{"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/optimal-brain-apoptosis","title":"Optimal Brain Apoptosis","arxiv_id":"2502.17941","date":"2025-02-25","proceeding":null,"authors":["Mingyuan Sun","Zheng Fang","Jiaxu Wang","Junjie Jiang","Delei Kong","Chenming Hu","Yuetong Fang","Renjing Xu"],"abstract":"The increasing complexity and parameter count of Convolutional Neural Networks (CNNs) and Transformers pose challenges in terms of computational efficiency and resource demands. Pruning has been identified as an effective strategy to address these challenges by removing redundant elements such as neurons, channels, or connections, thereby enhancing computational efficiency without heavily compromising performance. This paper builds on the foundational work of Optimal Brain Damage (OBD) by advancing the methodology of parameter importance estimation using the Hessian matrix. Unlike previous approaches that rely on approximations, we introduce Optimal Brain Apoptosis (OBA), a novel pruning method that calculates the Hessian-vector product value directly for each parameter. By decomposing the Hessian matrix across network layers and identifying conditions under which inter-layer Hessian submatrices are non-zero, we propose a highly efficient technique for computing the second-order Taylor expansion of parameters. This approach allows for a more precise pruning process, particularly in the context of CNNs and Transformers, as validated in our experiments including VGG19, ResNet32, ResNet50, and ViT-B/16 on CIFAR10, CIFAR100 and Imagenet datasets. Our code is available at https://github.com/NEU-REAL/OBA.","url_abs":"https://arxiv.org/abs/2502.17941v1","url_pdf":"https://arxiv.org/pdf/2502.17941v1.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":"optimal-brain-apoptosis","repo_url":"https://github.com/neu-real/oba","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.17941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.17941"}},"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":"deterministic:regex_extraction","url":"https://github.com/NEU-REAL/OBA","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/neu-real/oba","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"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":"915b7da0362eb2b4","entry":"is_scalar","repo":"NEU-REAL/OBA","repo_kind":"official","path":"torch_pruning/_helpers.py","file_url":"https://github.com/NEU-REAL/OBA/blob/HEAD/torch_pruning/_helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"915b7da0362eb2b4"}},{"code_sha256_prefix":"540fe9d9ed2115e9","entry":"cosine_sim","repo":"NEU-REAL/OBA","repo_kind":"official","path":"modules/models.py","file_url":"https://github.com/NEU-REAL/OBA/blob/HEAD/modules/models.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":"540fe9d9ed2115e9"}},{"code_sha256_prefix":"9c8a208b6e0b0e40","entry":"make_layers","repo":"NEU-REAL/OBA","repo_kind":"official","path":"modules/vgg.py","file_url":"https://github.com/NEU-REAL/OBA/blob/HEAD/modules/vgg.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":"9c8a208b6e0b0e40"}},{"code_sha256_prefix":"a5f40ecfcfcbe7c1","entry":"to_plain_idxs","repo":"NEU-REAL/OBA","repo_kind":"official","path":"torch_pruning/_helpers.py","file_url":"https://github.com/NEU-REAL/OBA/blob/HEAD/torch_pruning/_helpers.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":"a5f40ecfcfcbe7c1"}},{"code_sha256_prefix":"b4c2def331fc3065","entry":"to_root_idxs","repo":"NEU-REAL/OBA","repo_kind":"official","path":"torch_pruning/_helpers.py","file_url":"https://github.com/NEU-REAL/OBA/blob/HEAD/torch_pruning/_helpers.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":"b4c2def331fc3065"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}