{"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/online-learning-of-a-memory-for-learning","title":"Online Learning of a Memory for Learning Rates","arxiv_id":"1709.06709","date":"2017-09-20","proceeding":null,"authors":["Franziska Meier","Daniel Kappler","Stefan Schaal"],"abstract":"The promise of learning to learn for robotics rests on the hope that by\nextracting some information about the learning process itself we can speed up\nsubsequent similar learning tasks. Here, we introduce a computationally\nefficient online meta-learning algorithm that builds and optimizes a memory\nmodel of the optimal learning rate landscape from previously observed gradient\nbehaviors. While performing task specific optimization, this memory of learning\nrates predicts how to scale currently observed gradients. After applying the\ngradient scaling our meta-learner updates its internal memory based on the\nobserved effect its prediction had. Our meta-learner can be combined with any\ngradient-based optimizer, learns on the fly and can be transferred to new\noptimization tasks. In our evaluations we show that our meta-learning algorithm\nspeeds up learning of MNIST classification and a variety of learning control\ntasks, either in batch or online learning settings.","url_abs":"http://arxiv.org/abs/1709.06709v2","url_pdf":"http://arxiv.org/pdf/1709.06709v2.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":"online-learning-of-a-memory-for-learning","repo_url":"https://github.com/fmeier/online-meta-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.06709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.06709"}},"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/fmeier/online-meta-learning","reach":null}],"summary":{"ran_honours":2},"by_repo_kind":{"listed":{"samples":2,"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":"2b7dec8e2f8e9086","entry":"compute_class_rate","repo":"fmeier/online-meta-learning","repo_kind":"listed","path":"meta_learning/backend/pytorch/learning.py","file_url":"https://github.com/fmeier/online-meta-learning/blob/HEAD/meta_learning/backend/pytorch/learning.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":"2b7dec8e2f8e9086"}},{"code_sha256_prefix":"76b494bf18006d4f","entry":"compute_test_class_rate","repo":"fmeier/online-meta-learning","repo_kind":"listed","path":"meta_learning/backend/pytorch/learning.py","file_url":"https://github.com/fmeier/online-meta-learning/blob/HEAD/meta_learning/backend/pytorch/learning.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"76b494bf18006d4f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}