{"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/generalization-bounds","name":"Generalization Bounds","slug":"generalization-bounds","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":686,"papers_with_code":161,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"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":7,"rows_per_page":100,"shown":100,"of":686,"of_with_code":161,"tagged_in_all":686,"counts":{"archive_papers_tagged":686,"with_a_code_link":161,"where_syntology_ran_a_sample":55,"not_listed_spam_title":0,"listed":686,"listed_where_code_ran":55,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":45,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":45,"listed_every_run_a_failure_of_syntologys_instrument":10,"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/bridging-theory-and-algorithm-for-domain","slug":"bridging-theory-and-algorithm-for-domain","title":"Bridging Theory and Algorithm for Domain Adaptation","date":"2019-04-11","arxiv_id":"1904.05801","repositories_listed":6,"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/bridging-theory-and-algorithm-for-domain#ran","syntology_url":"https://syntology.ai/paper/1904.05801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05801"}},"official":{"repos":["thuml/MDD"],"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/domain-generalization-needs-stochastic-weight","slug":"domain-generalization-needs-stochastic-weight","title":"SWAD: Domain Generalization by Seeking Flat Minima","date":"2021-02-17","arxiv_id":"2102.08604","repositories_listed":4,"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":0,"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/domain-generalization-needs-stochastic-weight#ran","syntology_url":"https://syntology.ai/paper/2102.08604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.08604"}},"official":{"repos":["khanrc/swad"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/stable-sample-compression-schemes-new","slug":"stable-sample-compression-schemes-new","title":"Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound","date":"2020-11-09","arxiv_id":"2011.04586","repositories_listed":4,"syntology":null},{"url":"/paper/estimating-individual-treatment-effect","slug":"estimating-individual-treatment-effect","title":"Estimating individual treatment effect: generalization bounds and algorithms","date":"2016-06-13","arxiv_id":"1606.03976","repositories_listed":4,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/estimating-individual-treatment-effect#ran","syntology_url":"https://syntology.ai/paper/1606.03976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.03976"}},"official":null}},{"url":"/paper/robust-fine-tuning-of-deep-neural-networks","slug":"robust-fine-tuning-of-deep-neural-networks","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","date":"2022-06-06","arxiv_id":"2206.02659","repositories_listed":3,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"9 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; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/robust-fine-tuning-of-deep-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2206.02659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02659"}},"official":{"repos":["nerdsresearch/robust-fine-tuning","neu-statsml-research/robust-fine-tuning","virtuosoresearch/robust-fine-tuning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-an-explicit-hyperparameter","slug":"learning-an-explicit-hyperparameter","title":"Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks","date":"2021-07-06","arxiv_id":"2107.02378","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/a-surprising-linear-relationship-predicts","slug":"a-surprising-linear-relationship-predicts","title":"A Surprising Linear Relationship Predicts Test Performance in Deep Networks","date":"2018-07-25","arxiv_id":"1807.09659","repositories_listed":3,"syntology":null},{"url":"/paper/optimal-auctions-through-deep-learning","slug":"optimal-auctions-through-deep-learning","title":"Optimal Auctions through Deep Learning: Advances in Differentiable Economics","date":"2017-06-12","arxiv_id":"1706.03459","repositories_listed":3,"syntology":null},{"url":"/paper/computing-nonvacuous-generalization-bounds","slug":"computing-nonvacuous-generalization-bounds","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","date":"2017-03-31","arxiv_id":"1703.11008","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/computing-nonvacuous-generalization-bounds#ran","syntology_url":"https://syntology.ai/paper/1703.11008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.11008"}},"official":null}},{"url":"/paper/theoretical-insights-into-fine-tuning","slug":"theoretical-insights-into-fine-tuning","title":"Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization","date":"2024-10-03","arxiv_id":"2410.02247","repositories_listed":2,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 4 unverified","sample_list":"/paper/theoretical-insights-into-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2410.02247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02247"}},"official":{"repos":["chen123ctrls/efficientft","chen123CtrlS/LightweightAtt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-warm-start-fixed-point","slug":"learning-to-warm-start-fixed-point","title":"Learning to Warm-Start Fixed-Point Optimization Algorithms","date":"2023-09-14","arxiv_id":"2309.07835","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/learning-to-warm-start-fixed-point#ran","syntology_url":"https://syntology.ai/paper/2309.07835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07835"}},"official":{"repos":["stellatogrp/l2ws_fixed_point"],"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/generalization-in-graph-neural-networks","slug":"generalization-in-graph-neural-networks","title":"Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion","date":"2023-02-09","arxiv_id":"2302.04451","repositories_listed":2,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":2,"n_honours":4,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generalization-in-graph-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2302.04451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04451"}},"official":{"repos":["neu-statsml-research/generalization-in-graph-neural-networks","virtuosoresearch/generalization-in-graph-neural-networks"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/transformers-as-algorithms-generalization-and","slug":"transformers-as-algorithms-generalization-and","title":"Transformers as Algorithms: Generalization and Stability in In-context Learning","date":"2023-01-17","arxiv_id":"2301.07067","repositories_listed":2,"syntology":null},{"url":"/paper/nico-towards-better-benchmarking-for-domain","slug":"nico-towards-better-benchmarking-for-domain","title":"NICO++: Towards Better Benchmarking for Domain Generalization","date":"2022-04-17","arxiv_id":"2204.08040","repositories_listed":2,"syntology":null},{"url":"/paper/fast-interpretable-greedy-tree-sums-figs","slug":"fast-interpretable-greedy-tree-sums-figs","title":"Fast Interpretable Greedy-Tree Sums","date":"2022-01-28","arxiv_id":"2201.11931","repositories_listed":2,"syntology":null},{"url":"/paper/personalized-federated-learning-through-local","slug":"personalized-federated-learning-through-local","title":"Personalized Federated Learning through Local Memorization","date":"2021-11-17","arxiv_id":"2111.09360","repositories_listed":2,"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/personalized-federated-learning-through-local#ran","syntology_url":"https://syntology.ai/paper/2111.09360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09360"}},"official":{"repos":["omarfoq/knn-per"],"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/provable-guarantees-for-self-supervised-deep","slug":"provable-guarantees-for-self-supervised-deep","title":"Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss","date":"2021-06-08","arxiv_id":"2106.04156","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/provable-guarantees-for-self-supervised-deep#ran","syntology_url":"https://syntology.ai/paper/2106.04156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04156"}},"official":null}},{"url":"/paper/robust-generalization-despite-distribution","slug":"robust-generalization-despite-distribution","title":"Robust Generalization despite Distribution Shift via Minimum Discriminating Information","date":"2021-06-08","arxiv_id":"2106.04443","repositories_listed":2,"syntology":null},{"url":"/paper/function-approximation-via-sparse-random","slug":"function-approximation-via-sparse-random","title":"Generalization Bounds for Sparse Random Feature Expansions","date":"2021-03-04","arxiv_id":"2103.03191","repositories_listed":2,"syntology":null},{"url":"/paper/intrinsic-dimensionality-explains-the","slug":"intrinsic-dimensionality-explains-the","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","date":"2020-12-22","arxiv_id":"2012.13255","repositories_listed":2,"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/intrinsic-dimensionality-explains-the#ran","syntology_url":"https://syntology.ai/paper/2012.13255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.13255"}},"official":{"repos":["rabeehk/compacter"],"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/minimax-classification-with-0-1-loss-and","slug":"minimax-classification-with-0-1-loss-and","title":"Minimax Classification with 0-1 Loss and Performance Guarantees","date":"2020-10-15","arxiv_id":"2010.07964","repositories_listed":2,"syntology":null},{"url":"/paper/generalization-guarantees-for-multi-modal","slug":"generalization-guarantees-for-multi-modal","title":"Generalization Guarantees for Imitation Learning","date":"2020-08-05","arxiv_id":"2008.01913","repositories_listed":2,"syntology":null},{"url":"/paper/multi-task-reinforcement-learning-as-a-hidden","slug":"multi-task-reinforcement-learning-as-a-hidden","title":"Learning Robust State Abstractions for Hidden-Parameter Block MDPs","date":"2020-07-14","arxiv_id":"2007.07206","repositories_listed":2,"syntology":null},{"url":"/paper/pac-confidence-sets-for-deep-neural-networks-1","slug":"pac-confidence-sets-for-deep-neural-networks-1","title":"PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction","date":"2019-12-31","arxiv_id":"2001.00106","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/pac-confidence-sets-for-deep-neural-networks-1#ran","syntology_url":"https://syntology.ai/paper/2001.00106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.00106"}},"official":{"repos":["sangdon/PAC-confidence-set"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/globally-convergent-newton-methods-for-ill","slug":"globally-convergent-newton-methods-for-ill","title":"Globally Convergent Newton Methods for Ill-conditioned Generalized Self-concordant Losses","date":"2019-07-03","arxiv_id":"1907.01771","repositories_listed":2,"syntology":null},{"url":"/paper/deep-multi-wasserstein-unsupervised-domain","slug":"deep-multi-wasserstein-unsupervised-domain","title":"Deep multi-Wasserstein unsupervised domain adaptation","date":"2019-04-30","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/deep-learning-and-the-information-bottleneck","slug":"deep-learning-and-the-information-bottleneck","title":"Deep Learning and the Information Bottleneck Principle","date":"2015-03-09","arxiv_id":"1503.02406","repositories_listed":2,"syntology":null},{"url":"/paper/learning-where-to-learn-training-distribution","slug":"learning-where-to-learn-training-distribution","title":"Learning Where to Learn: Training Distribution Selection for Provable OOD Performance","date":"2025-05-27","arxiv_id":"2505.21626","repositories_listed":1,"syntology":null},{"url":"/paper/operator-learning-for-schrodinger-equation","slug":"operator-learning-for-schrodinger-equation","title":"Operator Learning for Schrödinger Equation: Unitarity, Error Bounds, and Time Generalization","date":"2025-05-23","arxiv_id":"2505.18288","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11298","slug":"2505-11298","title":"Graph Representational Learning: When Does More Expressivity Hurt Generalization?","date":"2025-05-16","arxiv_id":"2505.11298","repositories_listed":1,"syntology":null},{"url":"/paper/model-steering-learning-with-a-reference","slug":"model-steering-learning-with-a-reference","title":"Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws","date":"2025-05-10","arxiv_id":"2505.06699","repositories_listed":1,"syntology":null},{"url":"/paper/achieving-distributive-justice-in-federated","slug":"achieving-distributive-justice-in-federated","title":"Achieving Distributive Justice in Federated Learning via Uncertainty Quantification","date":"2025-04-22","arxiv_id":"2504.15924","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-transform-particle-filters","slug":"adversarial-transform-particle-filters","title":"Adversarial Transform Particle Filters","date":"2025-02-10","arxiv_id":"2502.06165","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-the-mechanisms-of-explicit-cot","slug":"unveiling-the-mechanisms-of-explicit-cot","title":"Unveiling the Mechanisms of Explicit CoT Training: How CoT Enhances Reasoning Generalization","date":"2025-02-07","arxiv_id":"2502.04667","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/unveiling-the-mechanisms-of-explicit-cot#ran","syntology_url":"https://syntology.ai/paper/2502.04667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04667"}},"official":{"repos":["chen123ctrls/t-cotmechanism"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-multi-task-learning-has-low-amortized","slug":"deep-multi-task-learning-has-low-amortized","title":"From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning","date":"2025-01-31","arxiv_id":"2501.19067","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-performance-of-hypergraph","slug":"generalization-performance-of-hypergraph","title":"Generalization Performance of Hypergraph Neural Networks","date":"2025-01-22","arxiv_id":"2501.12554","repositories_listed":1,"syntology":null},{"url":"/paper/the-complexity-dynamics-of-grokking","slug":"the-complexity-dynamics-of-grokking","title":"The Complexity Dynamics of Grokking","date":"2024-12-13","arxiv_id":"2412.09810","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-complexity-dynamics-of-grokking#ran","syntology_url":"https://syntology.ai/paper/2412.09810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09810"}},"official":{"repos":["brantondemoss/GrokkingComplexity"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generalization-bounds-via-conditional-f","slug":"generalization-bounds-via-conditional-f","title":"Generalization Bounds via Conditional $f$-Information","date":"2024-10-30","arxiv_id":"2410.22887","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalization-bounds-via-conditional-f#ran","syntology_url":"https://syntology.ai/paper/2410.22887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22887"}},"official":{"repos":["ZiqiaoWangGeothe/Conditional-f-Information-Bound"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-cold-posteriors-of-probabilistic-neural","slug":"on-cold-posteriors-of-probabilistic-neural","title":"On Cold Posteriors of Probabilistic Neural Networks: Understanding the Cold Posterior Effect and A New Way to Learn Cold Posteriors with Tight Generalization Guarantees","date":"2024-10-20","arxiv_id":"2410.15310","repositories_listed":1,"syntology":null},{"url":"/paper/sample-compression-unleashed-new","slug":"sample-compression-unleashed-new","title":"Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses","date":"2024-09-26","arxiv_id":"2409.17932","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-in-context-learning-performance","slug":"enhancing-in-context-learning-performance","title":"Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective","date":"2024-06-06","arxiv_id":"2406.03768","repositories_listed":1,"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/enhancing-in-context-learning-performance#ran","syntology_url":"https://syntology.ai/paper/2406.03768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03768"}},"official":{"repos":["chen123ctrls/enhancingicl_svdpruning"],"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/slicing-mutual-information-generalization","slug":"slicing-mutual-information-generalization","title":"Slicing Mutual Information Generalization Bounds for Neural Networks","date":"2024-06-06","arxiv_id":"2406.04047","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-limitations-of-fractal-dimension-as-a","slug":"on-the-limitations-of-fractal-dimension-as-a","title":"On the Limitations of Fractal Dimension as a Measure of Generalization","date":"2024-06-04","arxiv_id":"2406.02234","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-bound-and-new-algorithm-for","slug":"generalization-bound-and-new-algorithm-for","title":"Generalization Bound and New Algorithm for Clean-Label Backdoor Attack","date":"2024-06-02","arxiv_id":"2406.00588","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalization-bound-and-new-algorithm-for#ran","syntology_url":"https://syntology.ai/paper/2406.00588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00588"}},"official":{"repos":["hong-xian/backdoor-attack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generalization-bounds-for-causal-regression","slug":"generalization-bounds-for-causal-regression","title":"Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis","date":"2024-05-15","arxiv_id":"2405.09516","repositories_listed":1,"syntology":null},{"url":"/paper/pac-bayesian-generalization-bounds-for-2","slug":"pac-bayesian-generalization-bounds-for-2","title":"PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning","date":"2024-05-10","arxiv_id":"2405.06418","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 2 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) · 1 unverified","sample_list":"/paper/pac-bayesian-generalization-bounds-for-2#ran","syntology_url":"https://syntology.ai/paper/2405.06418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06418"}},"official":{"repos":["bdi-lab/reed"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/stability-and-generalization-in-free","slug":"stability-and-generalization-in-free","title":"Stability and Generalization in Free Adversarial Training","date":"2024-04-13","arxiv_id":"2404.08980","repositories_listed":1,"syntology":null},{"url":"/paper/a-pac-bayesian-framework-for-optimal-control","slug":"a-pac-bayesian-framework-for-optimal-control","title":"A PAC-Bayesian Framework for Optimal Control with Stability Guarantees","date":"2024-03-26","arxiv_id":"2403.17790","repositories_listed":1,"syntology":null},{"url":"/paper/do-generated-data-always-help-contrastive","slug":"do-generated-data-always-help-contrastive","title":"Do Generated Data Always Help Contrastive Learning?","date":"2024-03-19","arxiv_id":"2403.12448","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"6 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/do-generated-data-always-help-contrastive#ran","syntology_url":"https://syntology.ai/paper/2403.12448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12448"}},"official":{"repos":["pku-ml/adainf"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-pac-bayes-theory-and-gibbs","slug":"leveraging-pac-bayes-theory-and-gibbs","title":"Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures","date":"2024-02-19","arxiv_id":"2402.13285","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-bounds-for-heavy-tailed-sdes","slug":"generalization-bounds-for-heavy-tailed-sdes","title":"Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation","date":"2024-02-12","arxiv_id":"2402.07723","repositories_listed":1,"syntology":null},{"url":"/paper/digital-computers-break-the-curse-of","slug":"digital-computers-break-the-curse-of","title":"Tighter Learning Guarantees on Digital Computers via Concentration of Measure on Finite Spaces","date":"2024-02-08","arxiv_id":"2402.05576","repositories_listed":1,"syntology":null},{"url":"/paper/more-flexible-pac-bayesian-meta-learning-by","slug":"more-flexible-pac-bayesian-meta-learning-by","title":"More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms","date":"2024-02-06","arxiv_id":"2402.04054","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":2,"n_honours":7,"n_violates":0,"n_no_contract":0,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 7 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/more-flexible-pac-bayesian-meta-learning-by#ran","syntology_url":"https://syntology.ai/paper/2402.04054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04054"}},"official":{"repos":["hzakerinia/flexible-pac-bayes-meta-learning"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pac-bayesian-adversarially-robust","slug":"pac-bayesian-adversarially-robust","title":"PAC-Bayesian Adversarially Robust Generalization Bounds for Graph Neural Network","date":"2024-02-06","arxiv_id":"2402.04038","repositories_listed":1,"syntology":null},{"url":"/paper/minimum-description-length-and-generalization-1","slug":"minimum-description-length-and-generalization-1","title":"Minimum Description Length and Generalization Guarantees for Representation Learning","date":"2024-02-05","arxiv_id":"2402.03254","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/minimum-description-length-and-generalization-1#ran","syntology_url":"https://syntology.ai/paper/2402.03254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03254"}},"official":{"repos":["piotrkrasnowski/mdl_and_generalization_guarantees_for_representation_learning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-understanding-the-word-sensitivity-of","slug":"towards-understanding-the-word-sensitivity-of","title":"Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features","date":"2024-02-05","arxiv_id":"2402.02969","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-understanding-the-word-sensitivity-of#ran","syntology_url":"https://syntology.ai/paper/2402.02969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02969"}},"official":{"repos":["simone-bombari/attention-sensitivity"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/non-vacuous-generalization-bounds-for-large","slug":"non-vacuous-generalization-bounds-for-large","title":"Non-Vacuous Generalization Bounds for Large Language Models","date":"2023-12-28","arxiv_id":"2312.17173","repositories_listed":1,"syntology":{"n":38,"n_ran":13,"n_constructed":7,"n_ran_checked":10,"n_instrument":3,"n_unverified":25,"n_honours":1,"n_violates":2,"n_no_contract":7,"n_pointer_only":0,"phrase":"13 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 2 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 25 unverified","sample_list":"/paper/non-vacuous-generalization-bounds-for-large#ran","syntology_url":"https://syntology.ai/paper/2312.17173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17173"}},"official":{"repos":["sanaelotfi/sublora-bounds-for-llms"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":25,"ran_from_kinds":["official"]}}},{"url":"/paper/sequence-length-independent-norm-based","slug":"sequence-length-independent-norm-based","title":"Sequence Length Independent Norm-Based Generalization Bounds for Transformers","date":"2023-10-19","arxiv_id":"2310.13088","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/sequence-length-independent-norm-based#ran","syntology_url":"https://syntology.ai/paper/2310.13088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13088"}},"official":{"repos":["traugerjacob/transformer-gen-bounds"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/comparing-comparators-in-generalization","slug":"comparing-comparators-in-generalization","title":"Comparing Comparators in Generalization Bounds","date":"2023-10-16","arxiv_id":"2310.10534","repositories_listed":1,"syntology":null},{"url":"/paper/a-path-norm-toolkit-for-modern-networks","slug":"a-path-norm-toolkit-for-modern-networks","title":"A path-norm toolkit for modern networks: consequences, promises and challenges","date":"2023-10-02","arxiv_id":"2310.01225","repositories_listed":1,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/a-path-norm-toolkit-for-modern-networks#ran","syntology_url":"https://syntology.ai/paper/2310.01225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01225"}},"official":{"repos":["agonon/pathnorm_toolkit"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/implicit-graph-neural-diffusion-based-on","slug":"implicit-graph-neural-diffusion-based-on","title":"Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing","date":"2023-08-07","arxiv_id":"2308.03306","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/implicit-graph-neural-diffusion-based-on#ran","syntology_url":"https://syntology.ai/paper/2308.03306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03306"}},"official":{"repos":["guoji-fu/dignn"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-expressive-priors-for-generalization","slug":"learning-expressive-priors-for-generalization","title":"Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks","date":"2023-07-15","arxiv_id":"2307.07753","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"5 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; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/learning-expressive-priors-for-generalization#ran","syntology_url":"https://syntology.ai/paper/2307.07753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07753"}},"official":{"repos":["dlr-rm/bpnn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/how-does-information-bottleneck-help-deep","slug":"how-does-information-bottleneck-help-deep","title":"How Does Information Bottleneck Help Deep Learning?","date":"2023-05-30","arxiv_id":"2305.18887","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/how-does-information-bottleneck-help-deep#ran","syntology_url":"https://syntology.ai/paper/2305.18887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18887"}},"official":{"repos":["xu-ji/information-bottleneck"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/double-weighting-for-covariate-shift","slug":"double-weighting-for-covariate-shift","title":"Double-Weighting for Covariate Shift Adaptation","date":"2023-05-15","arxiv_id":"2305.08637","repositories_listed":1,"syntology":null},{"url":"/paper/towards-understanding-generalization-of-macro","slug":"towards-understanding-generalization-of-macro","title":"Towards Understanding Generalization of Macro-AUC in Multi-label Learning","date":"2023-05-09","arxiv_id":"2305.05248","repositories_listed":1,"syntology":null},{"url":"/paper/the-ideal-continual-learner-an-agent-that","slug":"the-ideal-continual-learner-an-agent-that","title":"The Ideal Continual Learner: An Agent That Never Forgets","date":"2023-04-29","arxiv_id":"2305.00316","repositories_listed":1,"syntology":null},{"url":"/paper/adaptergnn-efficient-delta-tuning-improves","slug":"adaptergnn-efficient-delta-tuning-improves","title":"AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNs","date":"2023-04-19","arxiv_id":"2304.09595","repositories_listed":1,"syntology":null},{"url":"/paper/energy-guided-entropic-neural-optimal","slug":"energy-guided-entropic-neural-optimal","title":"Energy-guided Entropic Neural Optimal Transport","date":"2023-04-12","arxiv_id":"2304.06094","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/energy-guided-entropic-neural-optimal#ran","syntology_url":"https://syntology.ai/paper/2304.06094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06094"}},"official":{"repos":["petrmokrov/energy-guided-entropic-ot"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/algorithm-dependent-bounds-for-representation","slug":"algorithm-dependent-bounds-for-representation","title":"Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation","date":"2023-04-04","arxiv_id":"2304.02064","repositories_listed":1,"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/algorithm-dependent-bounds-for-representation#ran","syntology_url":"https://syntology.ai/paper/2304.02064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.02064"}},"official":{"repos":["livreq/imda"],"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/uncertainty-calibration-for-counterfactual","slug":"uncertainty-calibration-for-counterfactual","title":"Uncertainty Calibration for Counterfactual Propensity Estimation in Recommendation","date":"2023-03-23","arxiv_id":"2303.12973","repositories_listed":1,"syntology":null},{"url":"/paper/transformed-low-rank-parameterization-can","slug":"transformed-low-rank-parameterization-can","title":"Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks","date":"2023-03-01","arxiv_id":"2303.00196","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transformed-low-rank-parameterization-can#ran","syntology_url":"https://syntology.ai/paper/2303.00196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.00196"}},"official":{"repos":["pingzaiwang/Analysis4TNN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pac-bayesian-generalization-bounds-for-1","slug":"pac-bayesian-generalization-bounds-for-1","title":"PAC-Bayesian Generalization Bounds for Adversarial Generative Models","date":"2023-02-17","arxiv_id":"2302.08942","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"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: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pac-bayesian-generalization-bounds-for-1#ran","syntology_url":"https://syntology.ai/paper/2302.08942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08942"}},"official":{"repos":["diarra2339/pac-bayes-wgan"],"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/perada-parameter-efficient-and-generalizable","slug":"perada-parameter-efficient-and-generalizable","title":"PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees","date":"2023-02-13","arxiv_id":"2302.06637","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-bounds-with-data-dependent","slug":"generalization-bounds-with-data-dependent","title":"Generalization Bounds with Data-dependent Fractal Dimensions","date":"2023-02-06","arxiv_id":"2302.02766","repositories_listed":1,"syntology":null},{"url":"/paper/tighter-information-theoretic-generalization","slug":"tighter-information-theoretic-generalization","title":"Tighter Information-Theoretic Generalization Bounds from Supersamples","date":"2023-02-05","arxiv_id":"2302.02432","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tighter-information-theoretic-generalization#ran","syntology_url":"https://syntology.ai/paper/2302.02432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.02432"}},"official":{"repos":["ZiqiaoWangGeothe/ld-single-CMI"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","unlocated"]}}},{"url":"/paper/learning-against-distributional-uncertainty","slug":"learning-against-distributional-uncertainty","title":"Learning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity","date":"2023-01-31","arxiv_id":"2301.13565","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-neural-operator-architectures-for","slug":"fine-tuning-neural-operator-architectures-for","title":"Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation","date":"2023-01-27","arxiv_id":"2301.11509","repositories_listed":1,"syntology":null},{"url":"/paper/non-iid-transfer-learning-on-graphs","slug":"non-iid-transfer-learning-on-graphs","title":"Non-IID Transfer Learning on Graphs","date":"2022-12-15","arxiv_id":"2212.08174","repositories_listed":1,"syntology":null},{"url":"/paper/pac-bayes-compression-bounds-so-tight-that","slug":"pac-bayes-compression-bounds-so-tight-that","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","date":"2022-11-24","arxiv_id":"2211.13609","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pac-bayes-compression-bounds-so-tight-that#ran","syntology_url":"https://syntology.ai/paper/2211.13609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13609"}},"official":{"repos":["activatedgeek/tight-pac-bayes"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/stability-analysis-and-generalization-bounds","slug":"stability-analysis-and-generalization-bounds","title":"Stability Analysis and Generalization Bounds of Adversarial Training","date":"2022-10-03","arxiv_id":"2210.00960","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-algorithm-dependent","slug":"exploring-the-algorithm-dependent","title":"Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability","date":"2022-09-27","arxiv_id":"2209.13262","repositories_listed":1,"syntology":null},{"url":"/paper/umix-improving-importance-weighting-for","slug":"umix-improving-importance-weighting-for","title":"UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup","date":"2022-09-19","arxiv_id":"2209.08928","repositories_listed":1,"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/umix-improving-importance-weighting-for#ran","syntology_url":"https://syntology.ai/paper/2209.08928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.08928"}},"official":{"repos":["tencentailabhealthcare/umix"],"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/integral-probability-metrics-pac-bayes-bounds","slug":"integral-probability-metrics-pac-bayes-bounds","title":"Integral Probability Metrics PAC-Bayes Bounds","date":"2022-07-01","arxiv_id":"2207.00614","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/integral-probability-metrics-pac-bayes-bounds#ran","syntology_url":"https://syntology.ai/paper/2207.00614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.00614"}},"official":{"repos":["ron-amit/pac_bayes_reg"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/trajectory-dependent-generalization-bounds","slug":"trajectory-dependent-generalization-bounds","title":"Learning Non-Vacuous Generalization Bounds from Optimization","date":"2022-06-09","arxiv_id":"2206.04359","repositories_listed":1,"syntology":null},{"url":"/paper/shedding-a-pac-bayesian-light-on-adaptive","slug":"shedding-a-pac-bayesian-light-on-adaptive","title":"Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances","date":"2022-06-07","arxiv_id":"2206.03230","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/shedding-a-pac-bayesian-light-on-adaptive#ran","syntology_url":"https://syntology.ai/paper/2206.03230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03230"}},"official":{"repos":["rubenohana/pac-bayesian_sliced-wasserstein"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rate-distortion-theoretic-bounds-on","slug":"rate-distortion-theoretic-bounds-on","title":"Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning","date":"2022-06-06","arxiv_id":"2206.02604","repositories_listed":1,"syntology":null},{"url":"/paper/capacity-bounds-for-the-deeponet-method-of","slug":"capacity-bounds-for-the-deeponet-method-of","title":"Towards Size-Independent Generalization Bounds for Deep Operator Nets","date":"2022-05-23","arxiv_id":"2205.11359","repositories_listed":1,"syntology":null},{"url":"/paper/chaotic-regularization-and-heavy-tailed","slug":"chaotic-regularization-and-heavy-tailed","title":"Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent","date":"2022-05-23","arxiv_id":"2205.11361","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chaotic-regularization-and-heavy-tailed#ran","syntology_url":"https://syntology.ai/paper/2205.11361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11361"}},"official":{"repos":["shoelim/mpgd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learnability-of-competitive-threshold-models","slug":"learnability-of-competitive-threshold-models","title":"Learnability of Competitive Threshold Models","date":"2022-05-08","arxiv_id":"2205.03750","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-through-the-lens-of-leave-one-1","slug":"generalization-through-the-lens-of-leave-one-1","title":"Generalization Through The Lens Of Leave-One-Out Error","date":"2022-03-07","arxiv_id":"2203.03443","repositories_listed":1,"syntology":null},{"url":"/paper/on-generalization-bounds-for-deep-networks","slug":"on-generalization-bounds-for-deep-networks","title":"On generalization bounds for deep networks based on loss surface implicit regularization","date":"2022-01-12","arxiv_id":"2201.04545","repositories_listed":1,"syntology":null},{"url":"/paper/simple-stochastic-and-online-gradient","slug":"simple-stochastic-and-online-gradient","title":"Simple Stochastic and Online Gradient DescentAlgorithms for Pairwise Learning","date":"2021-11-23","arxiv_id":"2111.12050","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simple-stochastic-and-online-gradient#ran","syntology_url":"https://syntology.ai/paper/2111.12050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12050"}},"official":{"repos":["zhenhuan-yang/simple-pairwise"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-the-generalization-benefit-of","slug":"understanding-the-generalization-benefit-of","title":"Understanding the Generalization Benefit of Model Invariance from a Data Perspective","date":"2021-11-10","arxiv_id":"2111.05529","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/understanding-the-generalization-benefit-of#ran","syntology_url":"https://syntology.ai/paper/2111.05529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.05529"}},"official":{"repos":["bangann/understanding-invariance"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-generalization-bounds-for-vc","slug":"improving-generalization-bounds-for-vc","title":"Improving Generalization Bounds for VC Classes Using the Hypergeometric Tail Inversion","date":"2021-10-29","arxiv_id":"2111.00062","repositories_listed":1,"syntology":null},{"url":"/paper/does-the-data-induce-capacity-control-in-deep","slug":"does-the-data-induce-capacity-control-in-deep","title":"Does the Data Induce Capacity Control in Deep Learning?","date":"2021-10-27","arxiv_id":"2110.14163","repositories_listed":1,"syntology":null},{"url":"/paper/survite-learning-heterogeneous-treatment","slug":"survite-learning-heterogeneous-treatment","title":"SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data","date":"2021-10-26","arxiv_id":"2110.14001","repositories_listed":1,"syntology":null},{"url":"/paper/quantum-boosting-using-domain-partitioning","slug":"quantum-boosting-using-domain-partitioning","title":"Quantum Boosting using Domain-Partitioning Hypotheses","date":"2021-10-25","arxiv_id":"2110.12793","repositories_listed":1,"syntology":null},{"url":"/paper/information-theoretic-generalization-bounds-3","slug":"information-theoretic-generalization-bounds-3","title":"Information-theoretic generalization bounds for black-box learning algorithms","date":"2021-10-04","arxiv_id":"2110.01584","repositories_listed":1,"syntology":null},{"url":"/paper/information-theoretic-generalization-bounds-4","slug":"information-theoretic-generalization-bounds-4","title":"Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning","date":"2021-10-03","arxiv_id":"2110.00926","repositories_listed":1,"syntology":null}],"syntology_records":40,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":55,"papers_where_code_ran_first_page":"/task/generalization-bounds/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":7,"url":"/task/generalization-bounds/papers/2","json":"/task/generalization-bounds/papers/2.json","rows":100},{"order":"archive","page":3,"of":7,"url":"/task/generalization-bounds/papers/3","json":"/task/generalization-bounds/papers/3.json","rows":100},{"order":"archive","page":4,"of":7,"url":"/task/generalization-bounds/papers/4","json":"/task/generalization-bounds/papers/4.json","rows":100},{"order":"archive","page":5,"of":7,"url":"/task/generalization-bounds/papers/5","json":"/task/generalization-bounds/papers/5.json","rows":100},{"order":"archive","page":6,"of":7,"url":"/task/generalization-bounds/papers/6","json":"/task/generalization-bounds/papers/6.json","rows":100},{"order":"archive","page":7,"of":7,"url":"/task/generalization-bounds/papers/7","json":"/task/generalization-bounds/papers/7.json","rows":86},{"order":"ran","page":1,"of":1,"url":"/task/generalization-bounds/papers/ran/1","json":"/task/generalization-bounds/papers/ran/1.json","rows":55}],"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":"b03139e387f10d5e7a78f17a45dd9cb065ef44dd0e46cafc5eb3d5c3dacebd00","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}