{"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/global-sparse-momentum-sgd-for-pruning-very","title":"Global Sparse Momentum SGD for Pruning Very Deep Neural Networks","arxiv_id":"1909.12778","date":"2019-09-27","proceeding":"NeurIPS 2019 12","authors":["Xiaohan Ding","Guiguang Ding","Xiangxin Zhou","Yuchen Guo","Jungong Han","Ji Liu"],"abstract":"Deep Neural Network (DNN) is powerful but computationally expensive and memory intensive, thus impeding its practical usage on resource-constrained front-end devices. DNN pruning is an approach for deep model compression, which aims at eliminating some parameters with tolerable performance degradation. In this paper, we propose a novel momentum-SGD-based optimization method to reduce the network complexity by on-the-fly pruning. Concretely, given a global compression ratio, we categorize all the parameters into two parts at each training iteration which are updated using different rules. In this way, we gradually zero out the redundant parameters, as we update them using only the ordinary weight decay but no gradients derived from the objective function. As a departure from prior methods that require heavy human works to tune the layer-wise sparsity ratios, prune by solving complicated non-differentiable problems or finetune the model after pruning, our method is characterized by 1) global compression that automatically finds the appropriate per-layer sparsity ratios; 2) end-to-end training; 3) no need for a time-consuming re-training process after pruning; and 4) superior capability to find better winning tickets which have won the initialization lottery.","url_abs":"https://arxiv.org/abs/1909.12778v3","url_pdf":"https://arxiv.org/pdf/1909.12778v3.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":"global-sparse-momentum-sgd-for-pruning-very","repo_url":"https://github.com/DingXiaoH/GSM-SGD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"global-sparse-momentum-sgd-for-pruning-very","repo_url":"https://github.com/ShawnDing1994/ACNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"global-sparse-momentum-sgd-for-pruning-very","repo_url":"https://github.com/ShawnDing1994/AOFP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"global-sparse-momentum-sgd-for-pruning-very","repo_url":"https://github.com/ShawnDing1994/Centripetal-SGD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"model-compression","task_name":"Model Compression"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1909.12778","atlas_url":"https://app.syntology.ai/?focus=1909.12778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.12778"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ShawnDing1994/Centripetal-SGD","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DingXiaoH/GSM-SGD","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ShawnDing1994/ACNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ShawnDing1994/AOFP","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"unverified":4},"by_repo_kind":{"listed":{"samples":5,"ran":1,"repositories":2}},"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":"e122dab1d91b8c35","entry":"make_divisible","repo":"ShawnDing1994/Centripetal-SGD","repo_kind":"listed","path":"constants.py","file_url":"https://github.com/ShawnDing1994/Centripetal-SGD/blob/HEAD/constants.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e122dab1d91b8c35"}},{"code_sha256_prefix":"15826dfdec9eddac","entry":"get_baseconfig_by_epoch","repo":"ShawnDing1994/ACNet","repo_kind":"listed","path":"base_config.py","file_url":"https://github.com/ShawnDing1994/ACNet/blob/HEAD/base_config.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":"15826dfdec9eddac"}},{"code_sha256_prefix":"52a95e3c59c0bef6","entry":"get_baseconfig_by_epoch","repo":"ShawnDing1994/Centripetal-SGD","repo_kind":"listed","path":"base_config.py","file_url":"https://github.com/ShawnDing1994/Centripetal-SGD/blob/HEAD/base_config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"52a95e3c59c0bef6"}},{"code_sha256_prefix":"ad0681cab624edde","entry":"rc_convert_flattened_deps","repo":"ShawnDing1994/Centripetal-SGD","repo_kind":"listed","path":"constants.py","file_url":"https://github.com/ShawnDing1994/Centripetal-SGD/blob/HEAD/constants.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ad0681cab624edde"}},{"code_sha256_prefix":"69c7110c918c4976","entry":"rc_origin_deps_flattened","repo":"ShawnDing1994/Centripetal-SGD","repo_kind":"listed","path":"constants.py","file_url":"https://github.com/ShawnDing1994/Centripetal-SGD/blob/HEAD/constants.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"69c7110c918c4976"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}