{"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/l4-practical-loss-based-stepsize-adaptation","title":"L4: Practical loss-based stepsize adaptation for deep learning","arxiv_id":"1802.05074","date":"2018-02-14","proceeding":"NeurIPS 2018 12","authors":["Michal Rolinek","Georg Martius"],"abstract":"We propose a stepsize adaptation scheme for stochastic gradient descent. It\noperates directly with the loss function and rescales the gradient in order to\nmake fixed predicted progress on the loss. We demonstrate its capabilities by\nconclusively improving the performance of Adam and Momentum optimizers. The\nenhanced optimizers with default hyperparameters consistently outperform their\nconstant stepsize counterparts, even the best ones, without a measurable\nincrease in computational cost. The performance is validated on multiple\narchitectures including dense nets, CNNs, ResNets, and the recurrent\nDifferential Neural Computer on classical datasets MNIST, fashion MNIST,\nCIFAR10 and others.","url_abs":"http://arxiv.org/abs/1802.05074v5","url_pdf":"http://arxiv.org/pdf/1802.05074v5.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":"l4-practical-loss-based-stepsize-adaptation","repo_url":"https://github.com/iovdin/l4-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"l4-practical-loss-based-stepsize-adaptation","repo_url":"https://github.com/martius-lab/l4-optimizer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.05074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05074"}},"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/iovdin/l4-pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/martius-lab/l4-optimizer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":"34e68c0f2b5e874f","entry":"n_inner_product","repo":"martius-lab/l4-optimizer","repo_kind":"listed","path":"L4/L4.py","file_url":"https://github.com/martius-lab/l4-optimizer/blob/HEAD/L4/L4.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":"34e68c0f2b5e874f"}},{"code_sha256_prefix":"a581df65f39b76fd","entry":"time_factor","repo":"martius-lab/l4-optimizer","repo_kind":"listed","path":"L4/L4.py","file_url":"https://github.com/martius-lab/l4-optimizer/blob/HEAD/L4/L4.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":"a581df65f39b76fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}