{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/stochastic-optimization","name":"Stochastic Optimization","slug":"stochastic-optimization","description_markdown":"**Stochastic Optimization** is the task of optimizing certain objective functional by generating and using stochastic random variables. Usually the Stochastic Optimization is an iterative process of generating random variables that progressively finds out the minima or the maxima of the objective functional. Stochastic Optimization is usually applied in the non-convex functional spaces where the usual deterministic optimization such as linear or quadratic programming or their variants cannot be used.\n\n\n<span class=\"description-source\">Source: [ASOC: An Adaptive Parameter-free Stochastic Optimization Techinique for Continuous Variables ](https://arxiv.org/abs/1506.08004)</span>","categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1387,"papers_with_code":337,"benchmarks":12,"benchmark_tables_in_archive":12,"benchmark_tables_shown":12,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":11,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/stochastic-optimization-on-cifar-10-wrn-28-10","slug":"stochastic-optimization-on-cifar-10-wrn-28-10","dataset":"CIFAR-10 WRN-28-10 - 200 Epochs","dataset_url":"/dataset/cifar-10","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Adam (eps-adjusted)","paper_title":"Domain-independent Dominance of Adaptive Methods","paper_url":"/paper/domain-independent-dominance-of-adaptive-1","paper_date":"2019-12-04","arxiv_id":"1912.01823","code_links":[{"title":"lolemacs/avagrad","url":"https://github.com/lolemacs/avagrad"}],"syntology":null}},{"leaderboard":"/sota/stochastic-optimization-on-cifar-100-wrn-28","slug":"stochastic-optimization-on-cifar-100-wrn-28","dataset":"CIFAR-100 WRN-28-10 - 200 Epochs","dataset_url":null,"rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"AvaGrad","paper_title":"Domain-independent Dominance of Adaptive Methods","paper_url":"/paper/domain-independent-dominance-of-adaptive-1","paper_date":"2019-12-04","arxiv_id":"1912.01823","code_links":[{"title":"lolemacs/avagrad","url":"https://github.com/lolemacs/avagrad"}],"syntology":null}},{"leaderboard":"/sota/stochastic-optimization-on-cifar-10-resnet-18","slug":"stochastic-optimization-on-cifar-10-resnet-18","dataset":"CIFAR-10 ResNet-18 - 200 Epochs","dataset_url":"/dataset/cifar-10","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SGD - cosine LR schedule","paper_title":"Benchopt: Reproducible, efficient and collaborative optimization benchmarks","paper_url":"/paper/benchopt-reproducible-efficient-and","paper_date":"2022-06-27","arxiv_id":"2206.13424","code_links":[{"title":"deepmind/optax","url":"https://github.com/deepmind/optax"},{"title":"google-deepmind/optax","url":"https://github.com/google-deepmind/optax"},{"title":"benchopt/benchopt","url":"https://github.com/benchopt/benchopt"}],"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/benchopt-reproducible-efficient-and#ran","syntology_url":"https://syntology.ai/paper/2206.13424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.13424"}},"official":{"repos":["benchopt/benchopt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/stochastic-optimization-on-imagenet-resnet-50-2","slug":"stochastic-optimization-on-imagenet-resnet-50-2","dataset":"ImageNet ResNet-50 - 90 Epochs","dataset_url":null,"rows_in_archive":4,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"AvaGrad","paper_title":"Domain-independent Dominance of Adaptive Methods","paper_url":"/paper/domain-independent-dominance-of-adaptive-1","paper_date":"2019-12-04","arxiv_id":"1912.01823","code_links":[{"title":"lolemacs/avagrad","url":"https://github.com/lolemacs/avagrad"}],"syntology":null}},{"leaderboard":"/sota/stochastic-optimization-on-penn-treebank","slug":"stochastic-optimization-on-penn-treebank","dataset":"Penn Treebank (Character Level) 3x1000 LSTM - 500 Epochs","dataset_url":"/dataset/penn-treebank","rows_in_archive":4,"metrics":["Bit per Character (BPC)"],"first_row_in_archive_order":{"model":"AvaGrad","paper_title":"Domain-independent Dominance of Adaptive Methods","paper_url":"/paper/domain-independent-dominance-of-adaptive-1","paper_date":"2019-12-04","arxiv_id":"1912.01823","code_links":[{"title":"lolemacs/avagrad","url":"https://github.com/lolemacs/avagrad"}],"syntology":null}},{"leaderboard":"/sota/stochastic-optimization-on-cifar-10","slug":"stochastic-optimization-on-cifar-10","dataset":"CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":2,"metrics":["Accuracy (max)","Accuracy (mean)"],"first_row_in_archive_order":{"model":"Resnet18","paper_title":"Mixing ADAM and SGD: a Combined Optimization Method","paper_url":"/paper/mixing-adam-and-sgd-a-combined-optimization","paper_date":"2020-11-16","arxiv_id":"2011.08042","code_links":[{"title":"nicolalandro/multi_optimizer","url":"https://gitlab.com/nicolalandro/multi_optimizer"}],"syntology":null}},{"leaderboard":"/sota/stochastic-optimization-on-cifar-100","slug":"stochastic-optimization-on-cifar-100","dataset":"CIFAR-100","dataset_url":"/dataset/cifar-100","rows_in_archive":2,"metrics":["Accuracy (max)","Accuracy (mean)"],"first_row_in_archive_order":{"model":"Resnet18","paper_title":"Mixing ADAM and SGD: a Combined Optimization Method","paper_url":"/paper/mixing-adam-and-sgd-a-combined-optimization","paper_date":"2020-11-16","arxiv_id":"2011.08042","code_links":[{"title":"nicolalandro/multi_optimizer","url":"https://gitlab.com/nicolalandro/multi_optimizer"}],"syntology":null}},{"leaderboard":"/sota/stochastic-optimization-on-imagenet-resnet-50","slug":"stochastic-optimization-on-imagenet-resnet-50","dataset":"ImageNet ResNet-50 - 50 Epochs","dataset_url":null,"rows_in_archive":2,"metrics":["Top 1 Accuracy","Top 5 Accuracy"],"first_row_in_archive_order":{"model":"Lookahead","paper_title":"Lookahead Optimizer: k steps forward, 1 step back","paper_url":"/paper/lookahead-optimizer-k-steps-forward-1-step","paper_date":"2019-07-19","arxiv_id":"1907.08610","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"alphadl/lookahead.pytorch","url":"https://github.com/alphadl/lookahead.pytorch"},{"title":"HamadYA/GhostFaceNets","url":"https://github.com/HamadYA/GhostFaceNets"},{"title":"michaelrzhang/lookahead","url":"https://github.com/michaelrzhang/lookahead"},{"title":"bojone/keras_lookahead","url":"https://github.com/bojone/keras_lookahead"},{"title":"201419/Optimizer-PyTorch","url":"https://github.com/201419/Optimizer-PyTorch"},{"title":"chizhu/BDC2019","url":"https://github.com/chizhu/BDC2019"},{"title":"wkcn/LookaheadOptimizer-mx","url":"https://github.com/wkcn/LookaheadOptimizer-mx"},{"title":"kpe/params-flow","url":"https://github.com/kpe/params-flow"},{"title":"nachiket273/lookahead_pytorch","url":"https://github.com/nachiket273/lookahead_pytorch"},{"title":"SdahlSean/RangerOptimizerTensorflow","url":"https://github.com/SdahlSean/RangerOptimizerTensorflow"},{"title":"allen108108/Model-Optimizer_Implementation","url":"https://github.com/allen108108/Model-Optimizer_Implementation"},{"title":"nsarang/lookahead_keras","url":"https://github.com/nsarang/lookahead_keras"},{"title":"DreamInvoker/LookaheadOptimizer-mx-implementation","url":"https://github.com/DreamInvoker/LookaheadOptimizer-mx-implementation"},{"title":"dseuss/pytorch-lookahead-optimizer","url":"https://github.com/dseuss/pytorch-lookahead-optimizer"},{"title":"mnikitin/LookaheadOptimizer-mx","url":"https://github.com/mnikitin/LookaheadOptimizer-mx"},{"title":"Abhimanyu08/Lookahead_Optimizer","url":"https://github.com/Abhimanyu08/Lookahead_Optimizer"},{"title":"zhangtj1996/lookahead-sgd-adam-rmsprop-","url":"https://github.com/zhangtj1996/lookahead-sgd-adam-rmsprop-"},{"title":"COMP6248-Reproducability-Challenge/LookaheadOptimizer","url":"https://github.com/COMP6248-Reproducability-Challenge/LookaheadOptimizer"}],"syntology":null}},{"leaderboard":"/sota/stochastic-optimization-on-imagenet-resnet-50-1","slug":"stochastic-optimization-on-imagenet-resnet-50-1","dataset":"ImageNet ResNet-50 - 60 Epochs","dataset_url":null,"rows_in_archive":2,"metrics":["Top 1 Accuracy","Top 5 Accuracy"],"first_row_in_archive_order":{"model":"Lookahead","paper_title":"Lookahead Optimizer: k steps forward, 1 step back","paper_url":"/paper/lookahead-optimizer-k-steps-forward-1-step","paper_date":"2019-07-19","arxiv_id":"1907.08610","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"alphadl/lookahead.pytorch","url":"https://github.com/alphadl/lookahead.pytorch"},{"title":"HamadYA/GhostFaceNets","url":"https://github.com/HamadYA/GhostFaceNets"},{"title":"michaelrzhang/lookahead","url":"https://github.com/michaelrzhang/lookahead"},{"title":"bojone/keras_lookahead","url":"https://github.com/bojone/keras_lookahead"},{"title":"201419/Optimizer-PyTorch","url":"https://github.com/201419/Optimizer-PyTorch"},{"title":"chizhu/BDC2019","url":"https://github.com/chizhu/BDC2019"},{"title":"wkcn/LookaheadOptimizer-mx","url":"https://github.com/wkcn/LookaheadOptimizer-mx"},{"title":"kpe/params-flow","url":"https://github.com/kpe/params-flow"},{"title":"nachiket273/lookahead_pytorch","url":"https://github.com/nachiket273/lookahead_pytorch"},{"title":"SdahlSean/RangerOptimizerTensorflow","url":"https://github.com/SdahlSean/RangerOptimizerTensorflow"},{"title":"allen108108/Model-Optimizer_Implementation","url":"https://github.com/allen108108/Model-Optimizer_Implementation"},{"title":"nsarang/lookahead_keras","url":"https://github.com/nsarang/lookahead_keras"},{"title":"DreamInvoker/LookaheadOptimizer-mx-implementation","url":"https://github.com/DreamInvoker/LookaheadOptimizer-mx-implementation"},{"title":"dseuss/pytorch-lookahead-optimizer","url":"https://github.com/dseuss/pytorch-lookahead-optimizer"},{"title":"mnikitin/LookaheadOptimizer-mx","url":"https://github.com/mnikitin/LookaheadOptimizer-mx"},{"title":"Abhimanyu08/Lookahead_Optimizer","url":"https://github.com/Abhimanyu08/Lookahead_Optimizer"},{"title":"zhangtj1996/lookahead-sgd-adam-rmsprop-","url":"https://github.com/zhangtj1996/lookahead-sgd-adam-rmsprop-"},{"title":"COMP6248-Reproducability-Challenge/LookaheadOptimizer","url":"https://github.com/COMP6248-Reproducability-Challenge/LookaheadOptimizer"}],"syntology":null}},{"leaderboard":"/sota/stochastic-optimization-on-ag-news","slug":"stochastic-optimization-on-ag-news","dataset":"AG News","dataset_url":"/dataset/ag-news","rows_in_archive":1,"metrics":["Accuracy (max)","Accuracy (mean)"],"first_row_in_archive_order":{"model":"Bert","paper_title":"Mixing ADAM and SGD: a Combined Optimization Method","paper_url":"/paper/mixing-adam-and-sgd-a-combined-optimization","paper_date":"2020-11-16","arxiv_id":"2011.08042","code_links":[{"title":"nicolalandro/multi_optimizer","url":"https://gitlab.com/nicolalandro/multi_optimizer"}],"syntology":null}},{"leaderboard":"/sota/stochastic-optimization-on-cola","slug":"stochastic-optimization-on-cola","dataset":"CoLA","dataset_url":"/dataset/cola","rows_in_archive":1,"metrics":["Accuracy (max)","Accuracy (mean)"],"first_row_in_archive_order":{"model":"Bert","paper_title":"Mixing ADAM and SGD: a Combined Optimization Method","paper_url":"/paper/mixing-adam-and-sgd-a-combined-optimization","paper_date":"2020-11-16","arxiv_id":"2011.08042","code_links":[{"title":"nicolalandro/multi_optimizer","url":"https://gitlab.com/nicolalandro/multi_optimizer"}],"syntology":null}},{"leaderboard":"/sota/stochastic-optimization-on-mnist","slug":"stochastic-optimization-on-mnist","dataset":"MNIST","dataset_url":"/dataset/mnist","rows_in_archive":1,"metrics":["NLL"],"first_row_in_archive_order":{"model":"MLP","paper_title":"Training Deep Networks without Learning Rates Through Coin Betting","paper_url":"/paper/training-deep-networks-without-learning-rates","paper_date":"2017-05-22","arxiv_id":"1705.07795","code_links":[{"title":"tensorflow/addons","url":"https://github.com/tensorflow/addons/blob/master/tensorflow_addons/optimizers/cocob.py"},{"title":"bremen79/parameterfree","url":"https://github.com/bremen79/parameterfree"},{"title":"bremen79/cocob","url":"https://github.com/bremen79/cocob"},{"title":"anandsaha/nips.cocob.pytorch","url":"https://github.com/anandsaha/nips.cocob.pytorch"},{"title":"nocotan/cocob_backprop","url":"https://github.com/nocotan/cocob_backprop"},{"title":"brendanxwhitaker/spred","url":"https://github.com/brendanxwhitaker/spred"}],"syntology":null}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045},{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/glue","name":"GLUE","full_name":"General Language Understanding Evaluation benchmark","num_papers_in_archive":3197},{"url":"/dataset/penn-treebank","name":"Penn Treebank","full_name":"","num_papers_in_archive":1006},{"url":"/dataset/ag-news","name":"AG News","full_name":"AG’s News Corpus","num_papers_in_archive":969},{"url":"/dataset/cola","name":"CoLA","full_name":"Corpus of Linguistic Acceptability","num_papers_in_archive":710},{"url":"/dataset/amazon-product-data","name":"Amazon Product Data","full_name":"rithik","num_papers_in_archive":41},{"url":"/dataset/mnist-8m","name":"MNIST-8M","full_name":"Infinite MNIST","num_papers_in_archive":26},{"url":"/dataset/msra-hand","name":"MSRA Hand","full_name":"MSRA Hand","num_papers_in_archive":15},{"url":"/dataset/opereid","name":"OpeReid","full_name":"OpeReid","num_papers_in_archive":3}],"subtasks":[{"url":"/task/distributed-optimization","name":"Distributed Optimization"},{"url":"/task/evolutionary-algorithms","name":"Evolutionary Algorithms"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":14,"rows_per_page":100,"shown":100,"of":1387,"of_with_code":337,"tagged_in_all":1387,"counts":{"archive_papers_tagged":1387,"with_a_code_link":337,"where_syntology_ran_a_sample":91,"not_listed_spam_title":0,"listed":1387,"listed_where_code_ran":91,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":74,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":74,"listed_every_run_a_failure_of_syntologys_instrument":17,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/adam-a-method-for-stochastic-optimization","slug":"adam-a-method-for-stochastic-optimization","title":"Adam: A Method for Stochastic Optimization","date":"2014-12-22","arxiv_id":"1412.6980","repositories_listed":87,"syntology":{"n":37,"n_ran":27,"n_constructed":7,"n_ran_checked":23,"n_instrument":4,"n_unverified":10,"n_honours":4,"n_violates":2,"n_no_contract":17,"n_pointer_only":8,"phrase":"27 ran (of which 7 constructed an object rather than computing a result; 23 with no instrument failure: 4 honoured, 2 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/adam-a-method-for-stochastic-optimization#ran","syntology_url":"https://syntology.ai/paper/1412.6980","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1412.6980"}},"official":null}},{"url":"/paper/accurate-large-minibatch-sgd-training","slug":"accurate-large-minibatch-sgd-training","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","date":"2017-06-08","arxiv_id":"1706.02677","repositories_listed":73,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/accurate-large-minibatch-sgd-training#ran","syntology_url":"https://syntology.ai/paper/1706.02677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.02677"}},"official":null}},{"url":"/paper/reducing-bert-pre-training-time-from-3-days","slug":"reducing-bert-pre-training-time-from-3-days","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","date":"2019-04-01","arxiv_id":"1904.00962","repositories_listed":32,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/reducing-bert-pre-training-time-from-3-days#ran","syntology_url":"https://syntology.ai/paper/1904.00962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00962"}},"official":{"repos":["tensorflow/addons"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/sgdr-stochastic-gradient-descent-with-warm","slug":"sgdr-stochastic-gradient-descent-with-warm","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","date":"2016-08-13","arxiv_id":"1608.03983","repositories_listed":24,"syntology":{"n":17,"n_ran":16,"n_constructed":7,"n_ran_checked":14,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":7,"phrase":"16 ran (of which 7 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sgdr-stochastic-gradient-descent-with-warm#ran","syntology_url":"https://syntology.ai/paper/1608.03983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.03983"}},"official":{"repos":["loshchil/SGDR"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/on-the-variance-of-the-adaptive-learning-rate","slug":"on-the-variance-of-the-adaptive-learning-rate","title":"On the Variance of the Adaptive Learning Rate and Beyond","date":"2019-08-08","arxiv_id":"1908.03265","repositories_listed":21,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/on-the-variance-of-the-adaptive-learning-rate#ran","syntology_url":"https://syntology.ai/paper/1908.03265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03265"}},"official":{"repos":["LiyuanLucasLiu/RAdam"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/lookahead-optimizer-k-steps-forward-1-step","slug":"lookahead-optimizer-k-steps-forward-1-step","title":"Lookahead Optimizer: k steps forward, 1 step back","date":"2019-07-19","arxiv_id":"1907.08610","repositories_listed":19,"syntology":null},{"url":"/paper/optimizing-neural-networks-with-kronecker","slug":"optimizing-neural-networks-with-kronecker","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","date":"2015-03-19","arxiv_id":"1503.05671","repositories_listed":19,"syntology":{"n":82,"n_ran":48,"n_constructed":20,"n_ran_checked":36,"n_instrument":12,"n_unverified":34,"n_honours":5,"n_violates":1,"n_no_contract":30,"n_pointer_only":7,"phrase":"48 ran (of which 20 constructed an object rather than computing a result; 36 with no instrument failure: 5 honoured, 1 violated, 30 with no contract checked; 12 where Syntology's instrument failed) · 34 unverified","sample_list":"/paper/optimizing-neural-networks-with-kronecker#ran","syntology_url":"https://syntology.ai/paper/1503.05671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1503.05671"}},"official":null}},{"url":"/paper/averaging-weights-leads-to-wider-optima-and","slug":"averaging-weights-leads-to-wider-optima-and","title":"Averaging Weights Leads to Wider Optima and Better Generalization","date":"2018-03-14","arxiv_id":"1803.05407","repositories_listed":17,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/averaging-weights-leads-to-wider-optima-and#ran","syntology_url":"https://syntology.ai/paper/1803.05407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.05407"}},"official":{"repos":["timgaripov/swa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deep-learning-with-elastic-averaging-sgd","slug":"deep-learning-with-elastic-averaging-sgd","title":"Deep learning with Elastic Averaging SGD","date":"2014-12-20","arxiv_id":"1412.6651","repositories_listed":10,"syntology":{"n":12,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/deep-learning-with-elastic-averaging-sgd#ran","syntology_url":"https://syntology.ai/paper/1412.6651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1412.6651"}},"official":{"repos":["sixin-zh/mpiT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/distributionally-robust-neural-networks-for","slug":"distributionally-robust-neural-networks-for","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","date":"2019-11-20","arxiv_id":"1911.08731","repositories_listed":8,"syntology":{"n":10,"n_ran":9,"n_constructed":3,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/distributionally-robust-neural-networks-for#ran","syntology_url":"https://syntology.ai/paper/1911.08731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08731"}},"official":{"repos":["kohpangwei/group_DRO","worksheets.codalab.org/worksheets/0x621811fe446b49bb818293bae2ef88c0"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/sophia-a-scalable-stochastic-second-order","slug":"sophia-a-scalable-stochastic-second-order","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","date":"2023-05-23","arxiv_id":"2305.14342","repositories_listed":7,"syntology":{"n":19,"n_ran":13,"n_constructed":4,"n_ran_checked":12,"n_instrument":1,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/sophia-a-scalable-stochastic-second-order#ran","syntology_url":"https://syntology.ai/paper/2305.14342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14342"}},"official":null}},{"url":"/paper/agnostic-federated-learning","slug":"agnostic-federated-learning","title":"Agnostic Federated Learning","date":"2019-02-01","arxiv_id":"1902.00146","repositories_listed":7,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agnostic-federated-learning#ran","syntology_url":"https://syntology.ai/paper/1902.00146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.00146"}},"official":null}},{"url":"/paper/training-deep-networks-without-learning-rates","slug":"training-deep-networks-without-learning-rates","title":"Training Deep Networks without Learning Rates Through Coin Betting","date":"2017-05-22","arxiv_id":"1705.07795","repositories_listed":6,"syntology":null},{"url":"/paper/variational-inference-a-review-for","slug":"variational-inference-a-review-for","title":"Variational Inference: A Review for Statisticians","date":"2016-01-04","arxiv_id":"1601.00670","repositories_listed":6,"syntology":null},{"url":"/paper/adaptivity-without-compromise-a-momentumized","slug":"adaptivity-without-compromise-a-momentumized","title":"Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization","date":"2021-01-26","arxiv_id":"2101.11075","repositories_listed":5,"syntology":null},{"url":"/paper/learning-concise-representations-for","slug":"learning-concise-representations-for","title":"Learning concise representations for regression by evolving networks of trees","date":"2018-07-03","arxiv_id":"1807.00981","repositories_listed":5,"syntology":null},{"url":"/paper/adafactor-adaptive-learning-rates-with","slug":"adafactor-adaptive-learning-rates-with","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","date":"2018-04-11","arxiv_id":"1804.04235","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adafactor-adaptive-learning-rates-with#ran","syntology_url":"https://syntology.ai/paper/1804.04235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.04235"}},"official":null}},{"url":"/paper/eve-a-gradient-based-optimization-method-with","slug":"eve-a-gradient-based-optimization-method-with","title":"Eve: A Gradient Based Optimization Method with Locally and Globally Adaptive Learning Rates","date":"2016-11-04","arxiv_id":"1611.01505","repositories_listed":5,"syntology":null},{"url":"/paper/robust-deep-auc-maximization-a-new-surrogate","slug":"robust-deep-auc-maximization-a-new-surrogate","title":"Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification","date":"2020-12-06","arxiv_id":"2012.03173","repositories_listed":4,"syntology":null},{"url":"/paper/personalized-federated-learning-with-moreau","slug":"personalized-federated-learning-with-moreau","title":"Personalized Federated Learning with Moreau Envelopes","date":"2020-06-16","arxiv_id":"2006.08848","repositories_listed":4,"syntology":null},{"url":"/paper/adahessian-an-adaptive-second-order-optimizer","slug":"adahessian-an-adaptive-second-order-optimizer","title":"ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning","date":"2020-06-01","arxiv_id":"2006.00719","repositories_listed":4,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/adahessian-an-adaptive-second-order-optimizer#ran","syntology_url":"https://syntology.ai/paper/2006.00719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.00719"}},"official":{"repos":["amirgholami/adahessian"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/federated-learning-over-wireless-networks","slug":"federated-learning-over-wireless-networks","title":"Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocation","date":"2019-10-29","arxiv_id":"1910.13067","repositories_listed":4,"syntology":null},{"url":"/paper/kronecker-determinantal-point-processes","slug":"kronecker-determinantal-point-processes","title":"Kronecker Determinantal Point Processes","date":"2016-05-26","arxiv_id":"1605.08374","repositories_listed":4,"syntology":null},{"url":"/paper/revisiting-distributed-synchronous-sgd","slug":"revisiting-distributed-synchronous-sgd","title":"Revisiting Distributed Synchronous SGD","date":"2016-04-04","arxiv_id":"1604.00981","repositories_listed":4,"syntology":null},{"url":"/paper/second-order-stochastic-optimization-for","slug":"second-order-stochastic-optimization-for","title":"Second-Order Stochastic Optimization for Machine Learning in Linear Time","date":"2016-02-12","arxiv_id":"1602.03943","repositories_listed":4,"syntology":null},{"url":"/paper/a-kronecker-factored-approximate-fisher","slug":"a-kronecker-factored-approximate-fisher","title":"A Kronecker-factored approximate Fisher matrix for convolution layers","date":"2016-02-03","arxiv_id":"1602.01407","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-kronecker-factored-approximate-fisher#ran","syntology_url":"https://syntology.ai/paper/1602.01407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.01407"}},"official":null}},{"url":"/paper/a-distributed-data-parallel-pytorch","slug":"a-distributed-data-parallel-pytorch","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","date":"2023-09-12","arxiv_id":"2309.06497","repositories_listed":3,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/a-distributed-data-parallel-pytorch#ran","syntology_url":"https://syntology.ai/paper/2309.06497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06497"}},"official":{"repos":["facebookresearch/optimizers"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/benchopt-reproducible-efficient-and","slug":"benchopt-reproducible-efficient-and","title":"Benchopt: Reproducible, efficient and collaborative optimization benchmarks","date":"2022-06-27","arxiv_id":"2206.13424","repositories_listed":3,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/benchopt-reproducible-efficient-and#ran","syntology_url":"https://syntology.ai/paper/2206.13424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.13424"}},"official":{"repos":["benchopt/benchopt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/differentiable-quality-diversity","slug":"differentiable-quality-diversity","title":"Differentiable Quality Diversity","date":"2021-06-07","arxiv_id":"2106.03894","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/differentiable-quality-diversity#ran","syntology_url":"https://syntology.ai/paper/2106.03894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03894"}},"official":{"repos":["icaros-usc/dqd","icaros-usc/pyribs"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/apollo-an-adaptive-parameter-wise-diagonal","slug":"apollo-an-adaptive-parameter-wise-diagonal","title":"Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization","date":"2020-09-28","arxiv_id":"2009.13586","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/apollo-an-adaptive-parameter-wise-diagonal#ran","syntology_url":"https://syntology.ai/paper/2009.13586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13586"}},"official":{"repos":["XuezheMax/apollo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/online-approximate-bayesian-learning","slug":"online-approximate-bayesian-learning","title":"A Global Stochastic Optimization Particle Filter Algorithm","date":"2020-07-09","arxiv_id":"2007.04803","repositories_listed":3,"syntology":null},{"url":"/paper/pacoh-bayes-optimal-meta-learning-with-pac","slug":"pacoh-bayes-optimal-meta-learning-with-pac","title":"PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees","date":"2020-02-13","arxiv_id":"2002.05551","repositories_listed":3,"syntology":null},{"url":"/paper/svgd-a-virtual-gradients-descent-method-for","slug":"svgd-a-virtual-gradients-descent-method-for","title":"SVGD: A Virtual Gradients Descent Method for Stochastic Optimization","date":"2019-07-09","arxiv_id":"1907.04021","repositories_listed":3,"syntology":null},{"url":"/paper/stochastic-gradient-methods-with-layer-wise","slug":"stochastic-gradient-methods-with-layer-wise","title":"Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks","date":"2019-05-27","arxiv_id":"1905.11286","repositories_listed":3,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stochastic-gradient-methods-with-layer-wise#ran","syntology_url":"https://syntology.ai/paper/1905.11286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11286"}},"official":null}},{"url":"/paper/a-contrastive-divergence-for-combining","slug":"a-contrastive-divergence-for-combining","title":"A Contrastive Divergence for Combining Variational Inference and MCMC","date":"2019-05-10","arxiv_id":"1905.04062","repositories_listed":3,"syntology":null},{"url":"/paper/on-the-convergence-of-adam-and-beyond-1","slug":"on-the-convergence-of-adam-and-beyond-1","title":"On the Convergence of Adam and Beyond","date":"2019-04-19","arxiv_id":"1904.09237","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-the-convergence-of-adam-and-beyond-1#ran","syntology_url":"https://syntology.ai/paper/1904.09237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09237"}},"official":null}},{"url":"/paper/cyclical-stochastic-gradient-mcmc-for","slug":"cyclical-stochastic-gradient-mcmc-for","title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","date":"2019-02-11","arxiv_id":"1902.03932","repositories_listed":3,"syntology":null},{"url":"/paper/decentralized-stochastic-optimization-and","slug":"decentralized-stochastic-optimization-and","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","date":"2019-02-01","arxiv_id":"1902.00340","repositories_listed":3,"syntology":null},{"url":"/paper/on-line-adaptative-curriculum-learning-for","slug":"on-line-adaptative-curriculum-learning-for","title":"On-line Adaptative Curriculum Learning for GANs","date":"2018-07-31","arxiv_id":"1808.00020","repositories_listed":3,"syntology":null},{"url":"/paper/fast-and-scalable-bayesian-deep-learning-by","slug":"fast-and-scalable-bayesian-deep-learning-by","title":"Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam","date":"2018-06-13","arxiv_id":"1806.04854","repositories_listed":3,"syntology":null},{"url":"/paper/a-pid-controller-approach-for-stochastic","slug":"a-pid-controller-approach-for-stochastic","title":"A PID Controller Approach for Stochastic Optimization of Deep Networks","date":"2018-06-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/shampoo-preconditioned-stochastic-tensor","slug":"shampoo-preconditioned-stochastic-tensor","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","date":"2018-02-26","arxiv_id":"1802.09568","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/shampoo-preconditioned-stochastic-tensor#ran","syntology_url":"https://syntology.ai/paper/1802.09568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.09568"}},"official":null}},{"url":"/paper/spectralnet-spectral-clustering-using-deep","slug":"spectralnet-spectral-clustering-using-deep","title":"SpectralNet: Spectral Clustering using Deep Neural Networks","date":"2018-01-04","arxiv_id":"1801.01587","repositories_listed":3,"syntology":null},{"url":"/paper/online-learning-rate-adaptation-with","slug":"online-learning-rate-adaptation-with","title":"Online Learning Rate Adaptation with Hypergradient Descent","date":"2017-03-14","arxiv_id":"1703.04782","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/online-learning-rate-adaptation-with#ran","syntology_url":"https://syntology.ai/paper/1703.04782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.04782"}},"official":{"repos":["gbaydin/hypergradient-descent"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-generalized-canonical-correlation","slug":"deep-generalized-canonical-correlation","title":"Deep Generalized Canonical Correlation Analysis","date":"2017-02-08","arxiv_id":"1702.02519","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deep-generalized-canonical-correlation#ran","syntology_url":"https://syntology.ai/paper/1702.02519","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.02519"}},"official":{"repos":["bitbucket.org/adrianbenton/dgcca-py3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/convex-optimization-algorithms-and-complexity","slug":"convex-optimization-algorithms-and-complexity","title":"Convex Optimization: Algorithms and Complexity","date":"2014-05-20","arxiv_id":"1405.4980","repositories_listed":3,"syntology":null},{"url":"/paper/mars-unleashing-the-power-of-variance","slug":"mars-unleashing-the-power-of-variance","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","date":"2024-11-15","arxiv_id":"2411.10438","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mars-unleashing-the-power-of-variance#ran","syntology_url":"https://syntology.ai/paper/2411.10438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10438"}},"official":{"repos":["AGI-Arena/MARS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/from-text-to-test-ai-generated-control","slug":"from-text-to-test-ai-generated-control","title":"From Text to Test: AI-Generated Control Software for Materials Science Instruments","date":"2024-06-23","arxiv_id":"2406.16224","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/from-text-to-test-ai-generated-control#ran","syntology_url":"https://syntology.ai/paper/2406.16224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16224"}},"official":{"repos":["nrel/de","nrel/keithley_gpt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-stochastic-optimization-approach-to-train","slug":"a-stochastic-optimization-approach-to-train","title":"Outlier-robust neural network training: variation regularization meets trimmed loss to prevent functional breakdown","date":"2023-08-04","arxiv_id":"2308.02293","repositories_listed":2,"syntology":null},{"url":"/paper/a-stochastic-optimization-approach-to","slug":"a-stochastic-optimization-approach-to","title":"Minimizing robust density power-based divergences for general parametric density models","date":"2023-07-11","arxiv_id":"2307.05251","repositories_listed":2,"syntology":null},{"url":"/paper/minimax-auc-fairness-efficient-algorithm-with","slug":"minimax-auc-fairness-efficient-algorithm-with","title":"Minimax AUC Fairness: Efficient Algorithm with Provable Convergence","date":"2022-08-22","arxiv_id":"2208.10451","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minimax-auc-fairness-efficient-algorithm-with#ran","syntology_url":"https://syntology.ai/paper/2208.10451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.10451"}},"official":{"repos":["zhenhuan-yang/minimaxfairauc"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/log-barriers-for-safe-black-box-optimization","slug":"log-barriers-for-safe-black-box-optimization","title":"Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning","date":"2022-07-21","arxiv_id":"2207.10415","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/log-barriers-for-safe-black-box-optimization#ran","syntology_url":"https://syntology.ai/paper/2207.10415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10415"}},"official":{"repos":["ilnura/lb_sgd","lasgroup/lbsgd-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/communication-efficient-adaptive-federated","slug":"communication-efficient-adaptive-federated","title":"Communication-Efficient Adaptive Federated Learning","date":"2022-05-05","arxiv_id":"2205.02719","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/communication-efficient-adaptive-federated#ran","syntology_url":"https://syntology.ai/paper/2205.02719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.02719"}},"official":null}},{"url":"/paper/exploiting-explainable-metrics-for-augmented","slug":"exploiting-explainable-metrics-for-augmented","title":"Exploiting Explainable Metrics for Augmented SGD","date":"2022-03-31","arxiv_id":"2203.16723","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-approximation-of-jacobian-matrices","slug":"efficient-approximation-of-jacobian-matrices","title":"Efficient approximation of Jacobian matrices involving a non-uniform fast Fourier transform (NUFFT)","date":"2021-11-04","arxiv_id":"2111.02912","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/efficient-approximation-of-jacobian-matrices#ran","syntology_url":"https://syntology.ai/paper/2111.02912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02912"}},"official":{"repos":["guanhuaw/Bjork"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/locally-differentially-private-federated","slug":"locally-differentially-private-federated","title":"Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses","date":"2021-06-17","arxiv_id":"2106.09779","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/locally-differentially-private-federated#ran","syntology_url":"https://syntology.ai/paper/2106.09779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09779"}},"official":{"repos":["lowya/Locally-Differentially-Private-Federated-Learning","lowya/private-federated-learning-without-a-trusted-server"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/polygonal-unadjusted-langevin-algorithms","slug":"polygonal-unadjusted-langevin-algorithms","title":"Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks","date":"2021-05-28","arxiv_id":"2105.13937","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/polygonal-unadjusted-langevin-algorithms#ran","syntology_url":"https://syntology.ai/paper/2105.13937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13937"}},"official":null}},{"url":"/paper/lira-learnable-imperceptible-and-robust","slug":"lira-learnable-imperceptible-and-robust","title":"LIRA: Learnable, Imperceptible and Robust Backdoor Attacks","date":"2021-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/quality-diversity-optimization-a-novel-branch","slug":"quality-diversity-optimization-a-novel-branch","title":"Quality-Diversity Optimization: a novel branch of stochastic optimization","date":"2020-12-08","arxiv_id":"2012.04322","repositories_listed":2,"syntology":null},{"url":"/paper/kernel-distributionally-robust-optimization","slug":"kernel-distributionally-robust-optimization","title":"Kernel Distributionally Robust Optimization","date":"2020-06-12","arxiv_id":"2006.06981","repositories_listed":2,"syntology":null},{"url":"/paper/s-addopt-decentralized-stochastic-first-order","slug":"s-addopt-decentralized-stochastic-first-order","title":"S-ADDOPT: Decentralized stochastic first-order optimization over directed graphs","date":"2020-05-15","arxiv_id":"2005.07785","repositories_listed":2,"syntology":null},{"url":"/paper/exponential-step-sizes-for-non-convex","slug":"exponential-step-sizes-for-non-convex","title":"A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance","date":"2020-02-12","arxiv_id":"2002.05273","repositories_listed":2,"syntology":null},{"url":"/paper/orl-reinforcement-learning-benchmarks-for","slug":"orl-reinforcement-learning-benchmarks-for","title":"ORL: Reinforcement Learning Benchmarks for Online Stochastic Optimization Problems","date":"2019-11-24","arxiv_id":"1911.10641","repositories_listed":2,"syntology":null},{"url":"/paper/continual-multi-task-gaussian-processes","slug":"continual-multi-task-gaussian-processes","title":"Continual Multi-task Gaussian Processes","date":"2019-10-31","arxiv_id":"1911.00002","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continual-multi-task-gaussian-processes#ran","syntology_url":"https://syntology.ai/paper/1911.00002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00002"}},"official":{"repos":["pmorenoz/ContinualGP"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/an-adaptive-and-momental-bound-method-for","slug":"an-adaptive-and-momental-bound-method-for","title":"An Adaptive and Momental Bound Method for Stochastic Learning","date":"2019-10-27","arxiv_id":"1910.12249","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-adaptive-and-momental-bound-method-for#ran","syntology_url":"https://syntology.ai/paper/1910.12249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12249"}},"official":{"repos":["lancopku/AdaMod"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/prior-specification-via-prior-predictive","slug":"prior-specification-via-prior-predictive","title":"Prior Specification for Bayesian Matrix Factorization via Prior Predictive Matching","date":"2019-10-27","arxiv_id":"1910.12263","repositories_listed":2,"syntology":null},{"url":"/paper/a-stochastic-first-order-method-for-ordered","slug":"a-stochastic-first-order-method-for-ordered","title":"Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization","date":"2019-07-09","arxiv_id":"1907.04371","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-stochastic-first-order-method-for-ordered#ran","syntology_url":"https://syntology.ai/paper/1907.04371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.04371"}},"official":{"repos":["kenjikawaguchi/qSGD"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/universal-boosting-variational-inference","slug":"universal-boosting-variational-inference","title":"Universal Boosting Variational Inference","date":"2019-06-04","arxiv_id":"1906.01235","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/universal-boosting-variational-inference#ran","syntology_url":"https://syntology.ai/paper/1906.01235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01235"}},"official":{"repos":["trevorcampbell/ubvi"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/trajectory-based-off-policy-deep","slug":"trajectory-based-off-policy-deep","title":"Trajectory-Based Off-Policy Deep Reinforcement Learning","date":"2019-05-14","arxiv_id":"1905.05710","repositories_listed":2,"syntology":null},{"url":"/paper/spi-optimizer-an-integral-separated-pi","slug":"spi-optimizer-an-integral-separated-pi","title":"SPI-Optimizer: an integral-Separated PI Controller for Stochastic Optimization","date":"2018-12-29","arxiv_id":"1812.11305","repositories_listed":2,"syntology":null},{"url":"/paper/hyperadam-a-learnable-task-adaptive-adam-for","slug":"hyperadam-a-learnable-task-adaptive-adam-for","title":"HyperAdam: A Learnable Task-Adaptive Adam for Network Training","date":"2018-11-22","arxiv_id":"1811.08996","repositories_listed":2,"syntology":null},{"url":"/paper/janossy-pooling-learning-deep-permutation","slug":"janossy-pooling-learning-deep-permutation","title":"Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs","date":"2018-11-05","arxiv_id":"1811.01900","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/janossy-pooling-learning-deep-permutation#ran","syntology_url":"https://syntology.ai/paper/1811.01900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.01900"}},"official":{"repos":["PurdueMINDS/JanossyPooling","balasrini33/JanossyPooling"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/quasi-hyperbolic-momentum-and-adam-for-deep","slug":"quasi-hyperbolic-momentum-and-adam-for-deep","title":"Quasi-hyperbolic momentum and Adam for deep learning","date":"2018-10-16","arxiv_id":"1810.06801","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/quasi-hyperbolic-momentum-and-adam-for-deep#ran","syntology_url":"https://syntology.ai/paper/1810.06801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.06801"}},"official":{"repos":["facebookresearch/qhoptim"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/spectral-inference-networks-unifying-spectral","slug":"spectral-inference-networks-unifying-spectral","title":"Spectral Inference Networks: Unifying Deep and Spectral Learning","date":"2018-06-06","arxiv_id":"1806.02215","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/spectral-inference-networks-unifying-spectral#ran","syntology_url":"https://syntology.ai/paper/1806.02215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02215"}},"official":{"repos":["deepmind/spectral_inference_networks"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-insufficiency-of-existing-momentum","slug":"on-the-insufficiency-of-existing-momentum","title":"On the insufficiency of existing momentum schemes for Stochastic Optimization","date":"2018-03-15","arxiv_id":"1803.05591","repositories_listed":2,"syntology":null},{"url":"/paper/online-variance-reduction-for-stochastic","slug":"online-variance-reduction-for-stochastic","title":"Online Variance Reduction for Stochastic Optimization","date":"2018-02-13","arxiv_id":"1802.04715","repositories_listed":2,"syntology":null},{"url":"/paper/a-deep-generative-model-for-gene-expression","slug":"a-deep-generative-model-for-gene-expression","title":"A deep generative model for gene expression profiles from single-cell RNA sequencing","date":"2017-09-07","arxiv_id":"1709.02082","repositories_listed":2,"syntology":null},{"url":"/paper/limited-memory-matrix-adaptation-for-large","slug":"limited-memory-matrix-adaptation-for-large","title":"Limited-Memory Matrix Adaptation for Large Scale Black-box Optimization","date":"2017-05-18","arxiv_id":"1705.06693","repositories_listed":2,"syntology":null},{"url":"/paper/reparameterization-gradients-through","slug":"reparameterization-gradients-through","title":"Reparameterization Gradients through Acceptance-Rejection Sampling Algorithms","date":"2016-10-18","arxiv_id":"1610.05683","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reparameterization-gradients-through#ran","syntology_url":"https://syntology.ai/paper/1610.05683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.05683"}},"official":{"repos":["blei-lab/ars-reparameterization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/convolutional-sketch-inversion","slug":"convolutional-sketch-inversion","title":"Convolutional Sketch Inversion","date":"2016-06-09","arxiv_id":"1606.03073","repositories_listed":2,"syntology":null},{"url":"/paper/learning-and-policy-search-in-stochastic","slug":"learning-and-policy-search-in-stochastic","title":"Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks","date":"2016-05-23","arxiv_id":"1605.07127","repositories_listed":2,"syntology":null},{"url":"/paper/black-box-variational-inference","slug":"black-box-variational-inference","title":"Black Box Variational Inference","date":"2013-12-31","arxiv_id":"1401.0118","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/black-box-variational-inference#ran","syntology_url":"https://syntology.ai/paper/1401.0118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1401.0118"}},"official":null}},{"url":"/paper/adaptive-semantic-token-communication-for","slug":"adaptive-semantic-token-communication-for","title":"Adaptive Semantic Token Communication for Transformer-based Edge Inference","date":"2025-05-23","arxiv_id":"2505.17604","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-optimization-with-orthogonality","slug":"efficient-optimization-with-orthogonality","title":"Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method","date":"2025-05-18","arxiv_id":"2505.12378","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/efficient-optimization-with-orthogonality#ran","syntology_url":"https://syntology.ai/paper/2505.12378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12378"}},"official":{"repos":["andyjm3/RSDM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/2505-11190","slug":"2505-11190","title":"JaxSGMC: Modular stochastic gradient MCMC in JAX","date":"2025-05-16","arxiv_id":"2505.11190","repositories_listed":1,"syntology":null},{"url":"/paper/sim-shapley-a-stable-and-computationally","slug":"sim-shapley-a-stable-and-computationally","title":"SIM-Shapley: A Stable and Computationally Efficient Approach to Shapley Value Approximation","date":"2025-05-13","arxiv_id":"2505.08198","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-subspace-generation-for-outlier","slug":"adversarial-subspace-generation-for-outlier","title":"Adversarial Subspace Generation for Outlier Detection in High-Dimensional Data","date":"2025-04-10","arxiv_id":"2504.07522","repositories_listed":1,"syntology":null},{"url":"/paper/catcma-with-margin-stochastic-optimization","slug":"catcma-with-margin-stochastic-optimization","title":"CatCMA with Margin: Stochastic Optimization for Continuous, Integer, and Categorical Variables","date":"2025-04-10","arxiv_id":"2504.07884","repositories_listed":1,"syntology":null},{"url":"/paper/semiparametric-counterfactual-regression","slug":"semiparametric-counterfactual-regression","title":"Semiparametric Counterfactual Regression","date":"2025-04-03","arxiv_id":"2504.02694","repositories_listed":1,"syntology":null},{"url":"/paper/decision-dependent-stochastic-optimization","slug":"decision-dependent-stochastic-optimization","title":"Decision-Dependent Stochastic Optimization: The Role of Distribution Dynamics","date":"2025-03-10","arxiv_id":"2503.07324","repositories_listed":1,"syntology":null},{"url":"/paper/navigating-demand-uncertainty-in-container","slug":"navigating-demand-uncertainty-in-container","title":"Navigating Demand Uncertainty in Container Shipping: Deep Reinforcement Learning for Enabling Adaptive and Feasible Master Stowage Planning","date":"2025-02-18","arxiv_id":"2502.12756","repositories_listed":1,"syntology":null},{"url":"/paper/a-novel-unified-parametric-assumption-for","slug":"a-novel-unified-parametric-assumption-for","title":"A Novel Unified Parametric Assumption for Nonconvex Optimization","date":"2025-02-17","arxiv_id":"2502.12329","repositories_listed":1,"syntology":null},{"url":"/paper/overshoot-taking-advantage-of-future","slug":"overshoot-taking-advantage-of-future","title":"Overshoot: Taking advantage of future gradients in momentum-based stochastic optimization","date":"2025-01-16","arxiv_id":"2501.09556","repositories_listed":1,"syntology":null},{"url":"/paper/averaged-adam-accelerates-stochastic","slug":"averaged-adam-accelerates-stochastic","title":"Averaged Adam accelerates stochastic optimization in the training of deep neural network approximations for partial differential equation and optimal control problems","date":"2025-01-10","arxiv_id":"2501.06081","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-adversarial-transferability-through-1","slug":"boosting-adversarial-transferability-through-1","title":"Boosting Adversarial Transferability through Augmentation in Hypothesis Space","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-nearly-optimal-single-loop-algorithm-for","slug":"a-nearly-optimal-single-loop-algorithm-for","title":"A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness","date":"2024-12-28","arxiv_id":"2412.20017","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-nearly-optimal-single-loop-algorithm-for#ran","syntology_url":"https://syntology.ai/paper/2412.20017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.20017"}},"official":{"repos":["MingruiLiu-ML-Lab/Single-Loop-bilevel-Optimizer-under-Unbounded-Smoothness"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bilevel-learning-with-inexact-stochastic","slug":"bilevel-learning-with-inexact-stochastic","title":"Bilevel Learning with Inexact Stochastic Gradients","date":"2024-12-16","arxiv_id":"2412.12049","repositories_listed":1,"syntology":null},{"url":"/paper/amclr-unified-augmented-learning-for-cross","slug":"amclr-unified-augmented-learning-for-cross","title":"AmCLR: Unified Augmented Learning for Cross-Modal Representations","date":"2024-12-10","arxiv_id":"2412.07979","repositories_listed":1,"syntology":null},{"url":"/paper/fixed-mean-gaussian-processes-for-post-hoc","slug":"fixed-mean-gaussian-processes-for-post-hoc","title":"Fixed-Mean Gaussian Processes for Post-hoc Bayesian Deep Learning","date":"2024-12-05","arxiv_id":"2412.04177","repositories_listed":1,"syntology":null},{"url":"/paper/conformal-symplectic-optimization-for-stable","slug":"conformal-symplectic-optimization-for-stable","title":"Conformal Symplectic Optimization for Stable Reinforcement Learning","date":"2024-12-03","arxiv_id":"2412.02291","repositories_listed":1,"syntology":null}],"syntology_records":42,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/stochastic-optimization-on-cifar-10-wrn-28-10","since_archive":"/sota/stochastic-optimization-on-cifar-10-wrn-28-10#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/stochastic-optimization-on-cifar-10-resnet-18","since_archive":"/sota/stochastic-optimization-on-cifar-10-resnet-18#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":91,"papers_where_code_ran_first_page":"/task/stochastic-optimization/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":14,"url":"/task/stochastic-optimization/papers/2","json":"/task/stochastic-optimization/papers/2.json","rows":100},{"order":"archive","page":3,"of":14,"url":"/task/stochastic-optimization/papers/3","json":"/task/stochastic-optimization/papers/3.json","rows":100},{"order":"archive","page":4,"of":14,"url":"/task/stochastic-optimization/papers/4","json":"/task/stochastic-optimization/papers/4.json","rows":100},{"order":"archive","page":5,"of":14,"url":"/task/stochastic-optimization/papers/5","json":"/task/stochastic-optimization/papers/5.json","rows":100},{"order":"archive","page":6,"of":14,"url":"/task/stochastic-optimization/papers/6","json":"/task/stochastic-optimization/papers/6.json","rows":100},{"order":"archive","page":7,"of":14,"url":"/task/stochastic-optimization/papers/7","json":"/task/stochastic-optimization/papers/7.json","rows":100},{"order":"archive","page":8,"of":14,"url":"/task/stochastic-optimization/papers/8","json":"/task/stochastic-optimization/papers/8.json","rows":100},{"order":"archive","page":9,"of":14,"url":"/task/stochastic-optimization/papers/9","json":"/task/stochastic-optimization/papers/9.json","rows":100},{"order":"archive","page":10,"of":14,"url":"/task/stochastic-optimization/papers/10","json":"/task/stochastic-optimization/papers/10.json","rows":100},{"order":"archive","page":11,"of":14,"url":"/task/stochastic-optimization/papers/11","json":"/task/stochastic-optimization/papers/11.json","rows":100},{"order":"archive","page":12,"of":14,"url":"/task/stochastic-optimization/papers/12","json":"/task/stochastic-optimization/papers/12.json","rows":100},{"order":"archive","page":13,"of":14,"url":"/task/stochastic-optimization/papers/13","json":"/task/stochastic-optimization/papers/13.json","rows":100},{"order":"archive","page":14,"of":14,"url":"/task/stochastic-optimization/papers/14","json":"/task/stochastic-optimization/papers/14.json","rows":87},{"order":"ran","page":1,"of":1,"url":"/task/stochastic-optimization/papers/ran/1","json":"/task/stochastic-optimization/papers/ran/1.json","rows":91}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"6bdcc4555145a523823625a90dfa1ed07144f81aafd63a12063d8698eca2146a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}