{"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/on-the-outsized-importance-of-learning-rates","title":"On the Outsized Importance of Learning Rates in Local Update Methods","arxiv_id":"2007.00878","date":"2020-07-02","proceeding":null,"authors":["Zachary Charles","Jakub Konečný"],"abstract":"We study a family of algorithms, which we refer to as local update methods, that generalize many federated learning and meta-learning algorithms. We prove that for quadratic objectives, local update methods perform stochastic gradient descent on a surrogate loss function which we exactly characterize. We show that the choice of client learning rate controls the condition number of that surrogate loss, as well as the distance between the minimizers of the surrogate and true loss functions. We use this theory to derive novel convergence rates for federated averaging that showcase this trade-off between the condition number of the surrogate loss and its alignment with the true loss function. We validate our results empirically, showing that in communication-limited settings, proper learning rate tuning is often sufficient to reach near-optimal behavior. We also present a practical method for automatic learning rate decay in local update methods that helps reduce the need for learning rate tuning, and highlight its empirical performance on a variety of tasks and datasets.","url_abs":"https://arxiv.org/abs/2007.00878v1","url_pdf":"https://arxiv.org/pdf/2007.00878v1.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":"on-the-outsized-importance-of-learning-rates","repo_url":"https://github.com/google-research/federated/tree/master/adaptive_lr_decay","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"maml","method_name":"MAML"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.00878","atlas_url":"https://app.syntology.ai/?focus=2007.00878","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":"2007.00878"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2007.00878\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2007.00878"},"call":"get_concepts_for_paper(arxiv_id=\"2007.00878\")"}],"by_repo":[{"repo":"google-research/federated","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["2010.05273","2102.03448","2107.06917","2302.03098"],"harvested_for_calls":[{"arxiv_id":"2010.05273","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.05273"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.05273\")"},{"arxiv_id":"2102.03448","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2102.03448"},"call":"get_harvested_code_for_paper(arxiv_id=\"2102.03448\")"},{"arxiv_id":"2107.06917","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2107.06917"},"call":"get_harvested_code_for_paper(arxiv_id=\"2107.06917\")"},{"arxiv_id":"2302.03098","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2302.03098"},"call":"get_harvested_code_for_paper(arxiv_id=\"2302.03098\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"725f89c265362a71bd1f4907db0faf860f7b03fdd4c8d8bc5bc821a7c332b5bc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}