{"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-to-learn-by-gradient-descent-by","title":"Learning to learn by gradient descent by gradient descent","arxiv_id":"1606.04474","date":"2016-06-14","proceeding":"NeurIPS 2016 12","authors":["Marcin Andrychowicz","Misha Denil","Sergio Gomez","Matthew W. Hoffman","David Pfau","Tom Schaul","Brendan Shillingford","Nando de Freitas"],"abstract":"The move from hand-designed features to learned features in machine learning\nhas been wildly successful. In spite of this, optimization algorithms are still\ndesigned by hand. In this paper we show how the design of an optimization\nalgorithm can be cast as a learning problem, allowing the algorithm to learn to\nexploit structure in the problems of interest in an automatic way. Our learned\nalgorithms, implemented by LSTMs, outperform generic, hand-designed competitors\non the tasks for which they are trained, and also generalize well to new tasks\nwith similar structure. We demonstrate this on a number of tasks, including\nsimple convex problems, training neural networks, and styling images with\nneural art.","url_abs":"http://arxiv.org/abs/1606.04474v2","url_pdf":"http://arxiv.org/pdf/1606.04474v2.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-to-learn-by-gradient-descent-by","repo_url":"https://github.com/deepmind/learning-to-learn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learning-to-learn-by-gradient-descent-by","repo_url":"https://github.com/DeepStudio-TW/LSTM-optimizer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"learning-to-learn-by-gradient-descent-by","repo_url":"https://github.com/ShuYuHuang/LSTM-optimizer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"learning-to-learn-by-gradient-descent-by","repo_url":"https://github.com/afoninandrei/opt-ml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-to-learn-by-gradient-descent-by","repo_url":"https://github.com/chenwydj/learning-to-learn-by-gradient-descent-by-gradient-descent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-learn-by-gradient-descent-by","repo_url":"https://github.com/teddykoker/learning-to-learn-jax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}},{"paper_slug":"learning-to-learn-by-gradient-descent-by","repo_url":"https://github.com/yangsenius/learning-to-learn-by-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-to-learn-by-gradient-descent-by","repo_url":"https://github.com/akshaykiranjose/L2O","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.04474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.04474"}},"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/ShuYuHuang/LSTM-optimizer","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenwydj/learning-to-learn-by-gradient-descent-by-gradient-descent","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/teddykoker/learning-to-learn-jax","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DeepStudio-TW/LSTM-optimizer","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/akshaykiranjose/L2O","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/learning-to-learn","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/afoninandrei/opt-ml","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangsenius/learning-to-learn-by-pytorch","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":2,"unverified":9},"by_repo_kind":{"official":{"samples":7,"ran":0,"repositories":1},"listed":{"samples":6,"ran":4,"repositories":2}},"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":"51aa3978682adacb","entry":"RMS","repo":"yangsenius/learning-to-learn-by-pytorch","repo_kind":"listed","path":"learning_to_learn.py","file_url":"https://github.com/yangsenius/learning-to-learn-by-pytorch/blob/HEAD/learning_to_learn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"51aa3978682adacb"}},{"code_sha256_prefix":"5618ad88931a7126","entry":"SGD","repo":"yangsenius/learning-to-learn-by-pytorch","repo_kind":"listed","path":"learning_to_learn.py","file_url":"https://github.com/yangsenius/learning-to-learn-by-pytorch/blob/HEAD/learning_to_learn.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5618ad88931a7126"}},{"code_sha256_prefix":"6f7f03d4cde2161b","entry":"f","repo":"yangsenius/learning-to-learn-by-pytorch","repo_kind":"listed","path":"learning_to_learn.py","file_url":"https://github.com/yangsenius/learning-to-learn-by-pytorch/blob/HEAD/learning_to_learn.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f7f03d4cde2161b"}},{"code_sha256_prefix":"a2f6a25906e664c5","entry":"to_var","repo":"chenwydj/learning-to-learn-by-gradient-descent-by-gradient-descent","repo_kind":"listed","path":"meta_module.py","file_url":"https://github.com/chenwydj/learning-to-learn-by-gradient-descent-by-gradient-descent/blob/HEAD/meta_module.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2f6a25906e664c5"}},{"code_sha256_prefix":"1c29584b2939883a","entry":"conv1x1","repo":"chenwydj/learning-to-learn-by-gradient-descent-by-gradient-descent","repo_kind":"listed","path":"resnet_meta.py","file_url":"https://github.com/chenwydj/learning-to-learn-by-gradient-descent-by-gradient-descent/blob/HEAD/resnet_meta.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":"1c29584b2939883a"}},{"code_sha256_prefix":"f743b7e6cb381d7e","entry":"conv3x3","repo":"chenwydj/learning-to-learn-by-gradient-descent-by-gradient-descent","repo_kind":"listed","path":"resnet_meta.py","file_url":"https://github.com/chenwydj/learning-to-learn-by-gradient-descent-by-gradient-descent/blob/HEAD/resnet_meta.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":"f743b7e6cb381d7e"}},{"code_sha256_prefix":"b69df76f969a0132","entry":"ensemble","repo":"deepmind/learning-to-learn","repo_kind":"official","path":"problems.py","file_url":"https://github.com/deepmind/learning-to-learn/blob/HEAD/problems.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":"b69df76f969a0132"}},{"code_sha256_prefix":"ea2e402a00d255b0","entry":"factory","repo":"deepmind/learning-to-learn","repo_kind":"official","path":"networks.py","file_url":"https://github.com/deepmind/learning-to-learn/blob/HEAD/networks.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":"ea2e402a00d255b0"}},{"code_sha256_prefix":"3b0a626884ce3fe7","entry":"get_default_net_config","repo":"deepmind/learning-to-learn","repo_kind":"official","path":"util.py","file_url":"https://github.com/deepmind/learning-to-learn/blob/HEAD/util.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":"3b0a626884ce3fe7"}},{"code_sha256_prefix":"111bd4a379a61c1f","entry":"get_net_path","repo":"deepmind/learning-to-learn","repo_kind":"official","path":"util.py","file_url":"https://github.com/deepmind/learning-to-learn/blob/HEAD/util.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":"111bd4a379a61c1f"}},{"code_sha256_prefix":"78582427a7b893ff","entry":"quadratic","repo":"deepmind/learning-to-learn","repo_kind":"official","path":"problems.py","file_url":"https://github.com/deepmind/learning-to-learn/blob/HEAD/problems.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":"78582427a7b893ff"}},{"code_sha256_prefix":"5802125d5f2e3a34","entry":"run_epoch","repo":"deepmind/learning-to-learn","repo_kind":"official","path":"util.py","file_url":"https://github.com/deepmind/learning-to-learn/blob/HEAD/util.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":"5802125d5f2e3a34"}},{"code_sha256_prefix":"2e3ea0020c003c64","entry":"simple_multi_optimizer","repo":"deepmind/learning-to-learn","repo_kind":"official","path":"problems.py","file_url":"https://github.com/deepmind/learning-to-learn/blob/HEAD/problems.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":"2e3ea0020c003c64"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}