{"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/eigendamage-structured-pruning-in-the","title":"EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis","arxiv_id":"1905.05934","date":"2019-05-15","proceeding":null,"authors":["Chaoqi Wang","Roger Grosse","Sanja Fidler","Guodong Zhang"],"abstract":"Reducing the test time resource requirements of a neural network while preserving test accuracy is crucial for running inference on resource-constrained devices. To achieve this goal, we introduce a novel network reparameterization based on the Kronecker-factored eigenbasis (KFE), and then apply Hessian-based structured pruning methods in this basis. As opposed to existing Hessian-based pruning algorithms which do pruning in parameter coordinates, our method works in the KFE where different weights are approximately independent, enabling accurate pruning and fast computation. We demonstrate empirically the effectiveness of the proposed method through extensive experiments. In particular, we highlight that the improvements are especially significant for more challenging datasets and networks. With negligible loss of accuracy, an iterative-pruning version gives a 10$\\times$ reduction in model size and a 8$\\times$ reduction in FLOPs on wide ResNet32.","url_abs":"https://arxiv.org/abs/1905.05934v1","url_pdf":"https://arxiv.org/pdf/1905.05934v1.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":"eigendamage-structured-pruning-in-the","repo_url":"https://github.com/alecwangcq/EigenDamage-Pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.05934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05934"}},"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/alecwangcq/EigenDamage-Pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"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":"a983a14792fc61ca","entry":"count_parameters","repo":"alecwangcq/EigenDamage-Pytorch","repo_kind":"official","path":"main_prune.py","file_url":"https://github.com/alecwangcq/EigenDamage-Pytorch/blob/HEAD/main_prune.py","link_basis":"first_harvest_node","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":"a983a14792fc61ca"}},{"code_sha256_prefix":"aebe352b9aca697d","entry":"get_bottleneck_builder","repo":"alecwangcq/EigenDamage-Pytorch","repo_kind":"official","path":"utils/network_utils.py","file_url":"https://github.com/alecwangcq/EigenDamage-Pytorch/blob/HEAD/utils/network_utils.py","link_basis":"first_harvest_node","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":"aebe352b9aca697d"}},{"code_sha256_prefix":"a0301d47d38fb19c","entry":"get_network","repo":"alecwangcq/EigenDamage-Pytorch","repo_kind":"official","path":"utils/network_utils.py","file_url":"https://github.com/alecwangcq/EigenDamage-Pytorch/blob/HEAD/utils/network_utils.py","link_basis":"first_harvest_node","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":"a0301d47d38fb19c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}