{"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/a-coefficient-makes-svrg-effective","title":"A Coefficient Makes SVRG Effective","arxiv_id":"2311.05589","date":"2023-11-09","proceeding":null,"authors":["Yida Yin","Zhiqiu Xu","Zhiyuan Li","Trevor Darrell","Zhuang Liu"],"abstract":"Stochastic Variance Reduced Gradient (SVRG), introduced by Johnson & Zhang (2013), is a theoretically compelling optimization method. However, as Defazio & Bottou (2019) highlight, its effectiveness in deep learning is yet to be proven. In this work, we demonstrate the potential of SVRG in optimizing real-world neural networks. Our empirical analysis finds that, for deeper neural networks, the strength of the variance reduction term in SVRG should be smaller and decrease as training progresses. Inspired by this, we introduce a multiplicative coefficient $\\alpha$ to control the strength and adjust it through a linear decay schedule. We name our method $\\alpha$-SVRG. Our results show $\\alpha$-SVRG better optimizes models, consistently reducing training loss compared to the baseline and standard SVRG across various model architectures and multiple image classification datasets. We hope our findings encourage further exploration into variance reduction techniques in deep learning. Code is available at github.com/davidyyd/alpha-SVRG.","url_abs":"https://arxiv.org/abs/2311.05589v2","url_pdf":"https://arxiv.org/pdf/2311.05589v2.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":"a-coefficient-makes-svrg-effective","repo_url":"https://github.com/davidyyd/alpha-svrg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.05589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05589"}},"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/davidyyd/alpha-SVRG","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/davidyyd/alpha-svrg","reach":{"status":"ok"}}],"summary":{"ran":8,"ran_violates":1,"ran_honours":1,"ran_fixture":1,"unverified":6},"by_repo_kind":{"official":{"samples":17,"ran":11,"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":17,"samples":[{"code_sha256_prefix":"2bafe6359f0924a9","entry":"Base_SVRG","repo":"davidyyd/alpha-svrg","repo_kind":"official","path":"svrg.py","file_url":"https://github.com/davidyyd/alpha-svrg/blob/HEAD/svrg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2bafe6359f0924a9"}},{"code_sha256_prefix":"cd147343a78b355b","entry":"Vanilla_SVRG","repo":"davidyyd/alpha-svrg","repo_kind":"official","path":"svrg.py","file_url":"https://github.com/davidyyd/alpha-svrg/blob/HEAD/svrg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd147343a78b355b"}},{"code_sha256_prefix":"9d57c9f8a153d267","entry":"build_transform","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9d57c9f8a153d267"}},{"code_sha256_prefix":"e0a8f99b321afef7","entry":"checkpoint_filter_fn","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"models/mlp_mixer.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/models/mlp_mixer.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e0a8f99b321afef7"}},{"code_sha256_prefix":"50338047d211322b","entry":"cosine_distance","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"svrg.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/svrg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"50338047d211322b"}},{"code_sha256_prefix":"5e1695210460b9d6","entry":"drop_scheduler","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"scheduler.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/scheduler.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5e1695210460b9d6"}},{"code_sha256_prefix":"6c1b7082e865f0e0","entry":"get_relative_position_index","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"models/swin_transformer.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/models/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6c1b7082e865f0e0"}},{"code_sha256_prefix":"1d7e5aed37e593e4","entry":"reg_scheduler","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"utils.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d7e5aed37e593e4"}},{"code_sha256_prefix":"b45f614a940e2c6d","entry":"svrg_scheduler","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"svrg.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/svrg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b45f614a940e2c6d"}},{"code_sha256_prefix":"993ae96666b00cb5","entry":"window_partition","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"models/swin_transformer.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/models/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"993ae96666b00cb5"}},{"code_sha256_prefix":"265c72d3ccc64544","entry":"window_reverse","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"models/swin_transformer.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/models/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"265c72d3ccc64544"}},{"code_sha256_prefix":"911ca22b0cc8ef70","entry":"build_dataset","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"911ca22b0cc8ef70"}},{"code_sha256_prefix":"490b21bf78e1dd8c","entry":"checkpoint_filter_fn","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"models/convnext.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/models/convnext.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"490b21bf78e1dd8c"}},{"code_sha256_prefix":"b700fb0a3496b255","entry":"cosine_scheduler","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"utils.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b700fb0a3496b255"}},{"code_sha256_prefix":"199223de2f9704cf","entry":"get_num_layer_for_convnext","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"optim_factory.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/optim_factory.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"199223de2f9704cf"}},{"code_sha256_prefix":"0ef0019514eaaa09","entry":"get_parameter_groups","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"optim_factory.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/optim_factory.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ef0019514eaaa09"}},{"code_sha256_prefix":"e543048349abd8f2","entry":"variance_metrics","repo":"davidyyd/alpha-SVRG","repo_kind":"official","path":"svrg.py","file_url":"https://github.com/davidyyd/alpha-SVRG/blob/HEAD/svrg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e543048349abd8f2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}