{"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/adaptivity-without-compromise-a-momentumized","title":"Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization","arxiv_id":"2101.11075","date":"2021-01-26","proceeding":null,"authors":["Aaron Defazio","Samy Jelassi"],"abstract":"We introduce MADGRAD, a novel optimization method in the family of AdaGrad adaptive gradient methods. MADGRAD shows excellent performance on deep learning optimization problems from multiple fields, including classification and image-to-image tasks in vision, and recurrent and bidirectionally-masked models in natural language processing. For each of these tasks, MADGRAD matches or outperforms both SGD and ADAM in test set performance, even on problems for which adaptive methods normally perform poorly.","url_abs":"https://arxiv.org/abs/2101.11075v3","url_pdf":"https://arxiv.org/pdf/2101.11075v3.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":"adaptivity-without-compromise-a-momentumized","repo_url":"https://github.com/facebookresearch/madgrad","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adaptivity-without-compromise-a-momentumized","repo_url":"https://github.com/DarshanDeshpande/tf-madgrad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adaptivity-without-compromise-a-momentumized","repo_url":"https://github.com/epsilon-deltta/ssd_guillotine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adaptivity-without-compromise-a-momentumized","repo_url":"https://github.com/mlverse/madgrad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adaptivity-without-compromise-a-momentumized","repo_url":"https://github.com/sdatkinson/madgrad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[{"method_slug":"adagrad","method_name":"AdaGrad"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"madgrad","method_name":"MADGRAD"},{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[{"slug":"madgrad","name":"MADGRAD","full_name":"Momentumized, adaptive, dual averaged gradient"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.11075","atlas_url":"https://app.syntology.ai/?focus=2101.11075","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":"2101.11075"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2101.11075\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2101.11075"},"call":"get_concepts_for_paper(arxiv_id=\"2101.11075\")"}],"by_repo":[{"repo":"facebookresearch/madgrad","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"DarshanDeshpande/tf-madgrad","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"epsilon-deltta/ssd_guillotine","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mlverse/madgrad","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sdatkinson/madgrad","kind":"listed","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":"2e961dca60b6bd92cf404f0b3892c868356ff33340fc497df6cf6945e24d7b4e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}