{"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/meta-learning-with-differentiable-closed-form","title":"Meta-learning with differentiable closed-form solvers","arxiv_id":"1805.08136","date":"2018-05-21","proceeding":"ICLR 2019 5","authors":["Luca Bertinetto","João F. Henriques","Philip H. S. Torr","Andrea Vedaldi"],"abstract":"Adapting deep networks to new concepts from a few examples is challenging, due to the high computational requirements of standard fine-tuning procedures. Most work on few-shot learning has thus focused on simple learning techniques for adaptation, such as nearest neighbours or gradient descent. Nonetheless, the machine learning literature contains a wealth of methods that learn non-deep models very efficiently. In this paper, we propose to use these fast convergent methods as the main adaptation mechanism for few-shot learning. The main idea is to teach a deep network to use standard machine learning tools, such as ridge regression, as part of its own internal model, enabling it to quickly adapt to novel data. This requires back-propagating errors through the solver steps. While normally the cost of the matrix operations involved in such a process would be significant, by using the Woodbury identity we can make the small number of examples work to our advantage. We propose both closed-form and iterative solvers, based on ridge regression and logistic regression components. Our methods constitute a simple and novel approach to the problem of few-shot learning and achieve performance competitive with or superior to the state of the art on three benchmarks.","url_abs":"https://arxiv.org/abs/1805.08136v3","url_pdf":"https://arxiv.org/pdf/1805.08136v3.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":"meta-learning-with-differentiable-closed-form","repo_url":"https://github.com/bertinetto/r2d2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"meta-learning-with-differentiable-closed-form","repo_url":"https://github.com/fiveai/on-episodes-fsl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"meta-learning-with-differentiable-closed-form","repo_url":"https://github.com/goldblum/AdversarialQuerying","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"meta-learning-with-differentiable-closed-form","repo_url":"https://github.com/icoz69/DeepEMD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"meta-learning-with-differentiable-closed-form","repo_url":"https://github.com/learnables/learn2learn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"form","task_name":"Form"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"logistic-regression","method_name":"Logistic Regression"}],"datasets_introduced":[{"slug":"cifar-fs","name":"CIFAR-FS","full_name":"CIFAR100 few-shots"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.08136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.08136"}},"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/fiveai/on-episodes-fsl","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/goldblum/AdversarialQuerying","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/icoz69/DeepEMD","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/learnables/learn2learn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bertinetto/r2d2","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":"fef2e2db16107a44","entry":"t_","repo":"bertinetto/r2d2","repo_kind":"listed","path":"fewshots/models/r2d2.py","file_url":"https://github.com/bertinetto/r2d2/blob/HEAD/fewshots/models/r2d2.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":"fef2e2db16107a44"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}