{"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":"/paper/domain-independent-dominance-of-adaptive-1","title":"Domain-independent Dominance of Adaptive Methods","arxiv_id":"1912.01823","date":"2019-12-04","proceeding":"CVPR 2021 1","authors":["Pedro Savarese","David Mcallester","Sudarshan Babu","Michael Maire"],"abstract":"From a simplified analysis of adaptive methods, we derive AvaGrad, a new optimizer which outperforms SGD on vision tasks when its adaptability is properly tuned. We observe that the power of our method is partially explained by a decoupling of learning rate and adaptability, greatly simplifying hyperparameter search. In light of this observation, we demonstrate that, against conventional wisdom, Adam can also outperform SGD on vision tasks, as long as the coupling between its learning rate and adaptability is taken into account. In practice, AvaGrad matches the best results, as measured by generalization accuracy, delivered by any existing optimizer (SGD or adaptive) across image classification (CIFAR, ImageNet) and character-level language modelling (Penn Treebank) tasks.","url_abs":"https://arxiv.org/abs/1912.01823v3","url_pdf":"https://arxiv.org/pdf/1912.01823v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"domain-independent-dominance-of-adaptive-1","repo_url":"https://github.com/lolemacs/avagrad","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/stochastic-optimization-on-cifar-10-wrn-28-10","task":"Stochastic Optimization","dataset":"CIFAR-10 WRN-28-10 - 200 Epochs","model":"Adam (eps-adjusted)","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"96.36"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-cifar-10-wrn-28-10","task":"Stochastic Optimization","dataset":"CIFAR-10 WRN-28-10 - 200 Epochs","model":"AvaGrad","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"96.2"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-cifar-10-wrn-28-10","task":"Stochastic Optimization","dataset":"CIFAR-10 WRN-28-10 - 200 Epochs","model":"SGD","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"96.14"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-cifar-10-wrn-28-10","task":"Stochastic Optimization","dataset":"CIFAR-10 WRN-28-10 - 200 Epochs","model":"AdaShift","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"95.92"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-cifar-10-wrn-28-10","task":"Stochastic Optimization","dataset":"CIFAR-10 WRN-28-10 - 200 Epochs","model":"AdamW","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy":"95.89"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-cifar-10-wrn-28-10","task":"Stochastic Optimization","dataset":"CIFAR-10 WRN-28-10 - 200 Epochs","model":"AdaBound","rank_in_archive_order":6,"of":6,"metrics":{"Accuracy":"94.6"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-cifar-100-wrn-28","task":"Stochastic Optimization","dataset":"CIFAR-100 WRN-28-10 - 200 Epochs","model":"AvaGrad","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"81.24"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-cifar-100-wrn-28","task":"Stochastic Optimization","dataset":"CIFAR-100 WRN-28-10 - 200 Epochs","model":"AdaShift","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"81.12"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-cifar-100-wrn-28","task":"Stochastic Optimization","dataset":"CIFAR-100 WRN-28-10 - 200 Epochs","model":"Adam (eps-adjusted)","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"81.04"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-cifar-100-wrn-28","task":"Stochastic Optimization","dataset":"CIFAR-100 WRN-28-10 - 200 Epochs","model":"SGD","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"80.95"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-cifar-100-wrn-28","task":"Stochastic Optimization","dataset":"CIFAR-100 WRN-28-10 - 200 Epochs","model":"AdamW","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy":"79.87"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-cifar-100-wrn-28","task":"Stochastic Optimization","dataset":"CIFAR-100 WRN-28-10 - 200 Epochs","model":"AdaBound","rank_in_archive_order":6,"of":6,"metrics":{"Accuracy":"77.24"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-imagenet-resnet-50-2","task":"Stochastic Optimization","dataset":"ImageNet ResNet-50 - 90 Epochs","model":"AvaGrad","rank_in_archive_order":1,"of":4,"metrics":{"Top 1 Accuracy":"76.51"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-imagenet-resnet-50-2","task":"Stochastic Optimization","dataset":"ImageNet ResNet-50 - 90 Epochs","model":"SGD","rank_in_archive_order":2,"of":4,"metrics":{"Top 1 Accuracy":"75.99"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-imagenet-resnet-50-2","task":"Stochastic Optimization","dataset":"ImageNet ResNet-50 - 90 Epochs","model":"AdamW","rank_in_archive_order":3,"of":4,"metrics":{"Top 1 Accuracy":"72.9"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-imagenet-resnet-50-2","task":"Stochastic Optimization","dataset":"ImageNet ResNet-50 - 90 Epochs","model":"AdaBound","rank_in_archive_order":4,"of":4,"metrics":{"Top 1 Accuracy":"72.01"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-penn-treebank","task":"Stochastic Optimization","dataset":"Penn Treebank (Character Level) 3x1000 LSTM - 500 Epochs","model":"AvaGrad","rank_in_archive_order":1,"of":4,"metrics":{"Bit per Character (BPC)":"1.175"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-penn-treebank","task":"Stochastic Optimization","dataset":"Penn Treebank (Character Level) 3x1000 LSTM - 500 Epochs","model":"AdamW","rank_in_archive_order":2,"of":4,"metrics":{"Bit per Character (BPC)":"1.23"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-penn-treebank","task":"Stochastic Optimization","dataset":"Penn Treebank (Character Level) 3x1000 LSTM - 500 Epochs","model":"AdaShift","rank_in_archive_order":3,"of":4,"metrics":{"Bit per Character (BPC)":"1.274"},"uses_additional_data":false},{"leaderboard":"/sota/stochastic-optimization-on-penn-treebank","task":"Stochastic Optimization","dataset":"Penn Treebank (Character Level) 3x1000 LSTM - 500 Epochs","model":"AdaBound","rank_in_archive_order":4,"of":4,"metrics":{"Bit per Character (BPC)":"2.863"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1912.01823","atlas_url":"https://app.syntology.ai/?focus=1912.01823","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1912.01823"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1912.01823\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1912.01823"},"call":"get_concepts_for_paper(arxiv_id=\"1912.01823\")"}],"by_repo":[{"repo":"lolemacs/avagrad","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5b9b72d989b7a74f26b907b194d7450c16000dd748a5846390e836bb94e3f3a9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}