{"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/learning-gradient-descent-better","title":"Learning Gradient Descent: Better Generalization and Longer Horizons","arxiv_id":"1703.03633","date":"2017-03-10","proceeding":"ICML 2017 8","authors":["Kaifeng Lv","Shunhua Jiang","Jian Li"],"abstract":"Training deep neural networks is a highly nontrivial task, involving\ncarefully selecting appropriate training algorithms, scheduling step sizes and\ntuning other hyperparameters. Trying different combinations can be quite\nlabor-intensive and time consuming. Recently, researchers have tried to use\ndeep learning algorithms to exploit the landscape of the loss function of the\ntraining problem of interest, and learn how to optimize over it in an automatic\nway. In this paper, we propose a new learning-to-learn model and some useful\nand practical tricks. Our optimizer outperforms generic, hand-crafted\noptimization algorithms and state-of-the-art learning-to-learn optimizers by\nDeepMind in many tasks. We demonstrate the effectiveness of our algorithms on a\nnumber of tasks, including deep MLPs, CNNs, and simple LSTMs.","url_abs":"http://arxiv.org/abs/1703.03633v3","url_pdf":"http://arxiv.org/pdf/1703.03633v3.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":"learning-gradient-descent-better","repo_url":"https://github.com/vfleaking/rnnprop","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-gradient-descent-better","repo_url":"https://github.com/daskol/paper-reviews","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"scheduling","task_name":"Scheduling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.03633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.03633"}},"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/daskol/paper-reviews","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vfleaking/rnnprop","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"30516a526744d5b9","entry":"lstm_func","repo":"vfleaking/rnnprop","repo_kind":"official","path":"optimizee/lstm.py","file_url":"https://github.com/vfleaking/rnnprop/blob/HEAD/optimizee/lstm.py","link_basis":"first_harvest_node","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":"30516a526744d5b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}