{"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/scheduling-the-learning-rate-via-1","title":"MARTHE: Scheduling the Learning Rate Via Online Hypergradients","arxiv_id":"1910.08525","date":"2019-10-18","proceeding":null,"authors":["Michele Donini","Luca Franceschi","Massimiliano Pontil","Orchid Majumder","Paolo Frasconi"],"abstract":"We study the problem of fitting task-specific learning rate schedules from the perspective of hyperparameter optimization, aiming at good generalization. We describe the structure of the gradient of a validation error w.r.t. the learning rate schedule -- the hypergradient. Based on this, we introduce MARTHE, a novel online algorithm guided by cheap approximations of the hypergradient that uses past information from the optimization trajectory to simulate future behaviour. It interpolates between two recent techniques, RTHO (Franceschi et al., 2017) and HD (Baydin et al. 2018), and is able to produce learning rate schedules that are more stable leading to models that generalize better.","url_abs":"https://arxiv.org/abs/1910.08525v4","url_pdf":"https://arxiv.org/pdf/1910.08525v4.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":"scheduling-the-learning-rate-via-1","repo_url":"https://github.com/awslabs/adatune","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"task_slug":"scheduling","task_name":"Scheduling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.08525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.08525"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/awslabs/adatune","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":"cd3bffe142e69f08","entry":"compute_loss_accuracy","repo":"awslabs/adatune","repo_kind":"official","path":"adatune/utils.py","file_url":"https://github.com/awslabs/adatune/blob/HEAD/adatune/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd3bffe142e69f08"}},{"code_sha256_prefix":"784ddae11e176a3a","entry":"data_loader","repo":"awslabs/adatune","repo_kind":"official","path":"adatune/data_loader.py","file_url":"https://github.com/awslabs/adatune/blob/HEAD/adatune/data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"784ddae11e176a3a"}},{"code_sha256_prefix":"3537855c9b0d860b","entry":"get_image_data_loader","repo":"awslabs/adatune","repo_kind":"official","path":"adatune/data_loader.py","file_url":"https://github.com/awslabs/adatune/blob/HEAD/adatune/data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3537855c9b0d860b"}},{"code_sha256_prefix":"e0f8a03ede43dce7","entry":"mnist_data_loader","repo":"awslabs/adatune","repo_kind":"official","path":"adatune/data_loader.py","file_url":"https://github.com/awslabs/adatune/blob/HEAD/adatune/data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e0f8a03ede43dce7"}},{"code_sha256_prefix":"0e72a2b0c495ab6f","entry":"network","repo":"awslabs/adatune","repo_kind":"official","path":"adatune/network.py","file_url":"https://github.com/awslabs/adatune/blob/HEAD/adatune/network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0e72a2b0c495ab6f"}},{"code_sha256_prefix":"6edde11b8ad65d09","entry":"resnet_18","repo":"awslabs/adatune","repo_kind":"official","path":"adatune/network.py","file_url":"https://github.com/awslabs/adatune/blob/HEAD/adatune/network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6edde11b8ad65d09"}},{"code_sha256_prefix":"9e639352522f81f3","entry":"resnet_34","repo":"awslabs/adatune","repo_kind":"official","path":"adatune/network.py","file_url":"https://github.com/awslabs/adatune/blob/HEAD/adatune/network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9e639352522f81f3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}