{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/benefits-of-learning-rate-annealing-for","title":"Benefits of Learning Rate Annealing for Tuning-Robustness in Stochastic Optimization","arxiv_id":"2503.09411","date":"2025-03-12","proceeding":null,"authors":["Amit Attia","Tomer Koren"],"abstract":"The learning rate in stochastic gradient methods is a critical hyperparameter that is notoriously costly to tune via standard grid search, especially for training modern large-scale models with billions of parameters. We identify a theoretical advantage of learning rate annealing schemes that decay the learning rate to zero at a polynomial rate, such as the widely-used cosine schedule, by demonstrating their increased robustness to initial parameter misspecification due to a coarse grid search. We present an analysis in a stochastic convex optimization setup demonstrating that the convergence rate of stochastic gradient descent with annealed schedules depends sublinearly on the multiplicative misspecification factor $\\rho$ (i.e., the grid resolution), achieving a rate of $O(\\rho^{1/(2p+1)}/\\sqrt{T})$ where $p$ is the degree of polynomial decay and $T$ is the number of steps, in contrast to the $O(\\rho/\\sqrt{T})$ rate that arises with fixed stepsizes and exhibits a linear dependence on $\\rho$. Experiments confirm the increased robustness compared to tuning with a fixed stepsize, that has significant implications for the computational overhead of hyperparameter search in practical training scenarios.","url_abs":"https://arxiv.org/abs/2503.09411v1","url_pdf":"https://arxiv.org/pdf/2503.09411v1.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":[],"tasks":[{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2503.09411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09411"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/bmsookim/wide-resnet.pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":5,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"00e569acd6b45ef0","entry":"conv3x3","repo":"bmsookim/wide-resnet.pytorch","repo_kind":"found_in_text","path":"networks/wide_resnet.py","file_url":"https://github.com/bmsookim/wide-resnet.pytorch/blob/HEAD/networks/wide_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00e569acd6b45ef0"}},{"code_sha256_prefix":"bb104479d26e39c3","entry":"get_hms","repo":"bmsookim/wide-resnet.pytorch","repo_kind":"found_in_text","path":"config.py","file_url":"https://github.com/bmsookim/wide-resnet.pytorch/blob/HEAD/config.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb104479d26e39c3"}},{"code_sha256_prefix":"5bf5755e73275b29","entry":"cfg","repo":"bmsookim/wide-resnet.pytorch","repo_kind":"found_in_text","path":"networks/resnet.py","file_url":"https://github.com/bmsookim/wide-resnet.pytorch/blob/HEAD/networks/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5bf5755e73275b29"}},{"code_sha256_prefix":"39ded92dbd260902","entry":"cfg","repo":"bmsookim/wide-resnet.pytorch","repo_kind":"found_in_text","path":"networks/vggnet.py","file_url":"https://github.com/bmsookim/wide-resnet.pytorch/blob/HEAD/networks/vggnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39ded92dbd260902"}},{"code_sha256_prefix":"947a620765d795b2","entry":"learning_rate","repo":"bmsookim/wide-resnet.pytorch","repo_kind":"found_in_text","path":"config.py","file_url":"https://github.com/bmsookim/wide-resnet.pytorch/blob/HEAD/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"947a620765d795b2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}