{"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-prune-deep-neural-networks-via","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","arxiv_id":"1705.07565","date":"2017-05-22","proceeding":"NeurIPS 2017 12","authors":["Xin Dong","Shangyu Chen","Sinno Jialin Pan"],"abstract":"How to develop slim and accurate deep neural networks has become crucial for\nreal- world applications, especially for those employed in embedded systems.\nThough previous work along this research line has shown some promising results,\nmost existing methods either fail to significantly compress a well-trained deep\nnetwork or require a heavy retraining process for the pruned deep network to\nre-boost its prediction performance. In this paper, we propose a new layer-wise\npruning method for deep neural networks. In our proposed method, parameters of\neach individual layer are pruned independently based on second order\nderivatives of a layer-wise error function with respect to the corresponding\nparameters. We prove that the final prediction performance drop after pruning\nis bounded by a linear combination of the reconstructed errors caused at each\nlayer. Therefore, there is a guarantee that one only needs to perform a light\nretraining process on the pruned network to resume its original prediction\nperformance. We conduct extensive experiments on benchmark datasets to\ndemonstrate the effectiveness of our pruning method compared with several\nstate-of-the-art baseline methods.","url_abs":"http://arxiv.org/abs/1705.07565v2","url_pdf":"http://arxiv.org/pdf/1705.07565v2.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-prune-deep-neural-networks-via","repo_url":"https://github.com/csyhhu/L-OBS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-prune-deep-neural-networks-via","repo_url":"https://github.com/EgoRedMC/pytorch_OBS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1705.07565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.07565"}},"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/csyhhu/L-OBS","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/EgoRedMC/pytorch_OBS","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":1,"samples":[{"code_sha256_prefix":"dbeac48285505a38","entry":"copy_net","repo":"EgoRedMC/pytorch_OBS","repo_kind":"listed","path":"NNet.py","file_url":"https://github.com/EgoRedMC/pytorch_OBS/blob/HEAD/NNet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dbeac48285505a38"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}