{"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/on-the-computational-efficiency-of-training","title":"On the Computational Efficiency of Training Neural Networks","arxiv_id":"1410.1141","date":"2014-10-05","proceeding":"NeurIPS 2014 12","authors":["Roi Livni","Shai Shalev-Shwartz","Ohad Shamir"],"abstract":"It is well-known that neural networks are computationally hard to train. On\nthe other hand, in practice, modern day neural networks are trained efficiently\nusing SGD and a variety of tricks that include different activation functions\n(e.g. ReLU), over-specification (i.e., train networks which are larger than\nneeded), and regularization. In this paper we revisit the computational\ncomplexity of training neural networks from a modern perspective. We provide\nboth positive and negative results, some of them yield new provably efficient\nand practical algorithms for training certain types of neural networks.","url_abs":"http://arxiv.org/abs/1410.1141v2","url_pdf":"http://arxiv.org/pdf/1410.1141v2.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":"on-the-computational-efficiency-of-training","repo_url":"https://github.com/scikit-learn-contrib/polylearn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"}],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1410.1141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1410.1141"}},"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/scikit-learn-contrib/polylearn","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":"f3935c661456f977","entry":"anova_kernel","repo":"scikit-learn-contrib/polylearn","repo_kind":"listed","path":"polylearn/kernels.py","file_url":"https://github.com/scikit-learn-contrib/polylearn/blob/HEAD/polylearn/kernels.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f3935c661456f977"}},{"code_sha256_prefix":"0d70a2ae9110607c","entry":"homogeneous_kernel","repo":"scikit-learn-contrib/polylearn","repo_kind":"listed","path":"polylearn/kernels.py","file_url":"https://github.com/scikit-learn-contrib/polylearn/blob/HEAD/polylearn/kernels.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0d70a2ae9110607c"}},{"code_sha256_prefix":"633103dfbd1f40db","entry":"safe_power","repo":"scikit-learn-contrib/polylearn","repo_kind":"listed","path":"polylearn/kernels.py","file_url":"https://github.com/scikit-learn-contrib/polylearn/blob/HEAD/polylearn/kernels.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"633103dfbd1f40db"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}