{"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-stochastic-first-order-method-for-ordered","title":"Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization","arxiv_id":"1907.04371","date":"2019-07-09","proceeding":null,"authors":["Kenji Kawaguchi","Haihao Lu"],"abstract":"We propose a new stochastic optimization framework for empirical risk minimization problems such as those that arise in machine learning. The traditional approaches, such as (mini-batch) stochastic gradient descent (SGD), utilize an unbiased gradient estimator of the empirical average loss. In contrast, we develop a computationally efficient method to construct a gradient estimator that is purposely biased toward those observations with higher current losses. On the theory side, we show that the proposed method minimizes a new ordered modification of the empirical average loss, and is guaranteed to converge at a sublinear rate to a global optimum for convex loss and to a critical point for weakly convex (non-convex) loss. Furthermore, we prove a new generalization bound for the proposed algorithm. On the empirical side, the numerical experiments show that our proposed method consistently improves the test errors compared with the standard mini-batch SGD in various models including SVM, logistic regression, and deep learning problems.","url_abs":"https://arxiv.org/abs/1907.04371v5","url_pdf":"https://arxiv.org/pdf/1907.04371v5.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-stochastic-first-order-method-for-ordered","repo_url":"https://github.com/kenjikawaguchi/qSGD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-stochastic-first-order-method-for-ordered","repo_url":"https://github.com/k9k2/qSGD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.04371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.04371"}},"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/k9k2/qSGD","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kenjikawaguchi/qSGD","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"kenjikawaguchi/qSGD","repo_kind":"official","path":"cifar10_WideResNet/models/cifar/resnet.py","file_url":"https://github.com/kenjikawaguchi/qSGD/blob/HEAD/cifar10_WideResNet/models/cifar/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"61182bd4fcf9cc8d","entry":"PreActResNet18","repo":"kenjikawaguchi/qSGD","repo_kind":"official","path":"models/preact_resnet.py","file_url":"https://github.com/kenjikawaguchi/qSGD/blob/HEAD/models/preact_resnet.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":"61182bd4fcf9cc8d"}},{"code_sha256_prefix":"c87e7665fde6cdfc","entry":"colorize","repo":"kenjikawaguchi/qSGD","repo_kind":"official","path":"cifar10_WideResNet/utils/visualize.py","file_url":"https://github.com/kenjikawaguchi/qSGD/blob/HEAD/cifar10_WideResNet/utils/visualize.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":"c87e7665fde6cdfc"}},{"code_sha256_prefix":"d66f0a3cbb86204c","entry":"gauss","repo":"kenjikawaguchi/qSGD","repo_kind":"official","path":"cifar10_WideResNet/utils/visualize.py","file_url":"https://github.com/kenjikawaguchi/qSGD/blob/HEAD/cifar10_WideResNet/utils/visualize.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":"d66f0a3cbb86204c"}},{"code_sha256_prefix":"1d6e2edb8832d7b0","entry":"get_mean_and_std","repo":"kenjikawaguchi/qSGD","repo_kind":"official","path":"cifar10_WideResNet/utils/misc.py","file_url":"https://github.com/kenjikawaguchi/qSGD/blob/HEAD/cifar10_WideResNet/utils/misc.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":"1d6e2edb8832d7b0"}},{"code_sha256_prefix":"1394422d51c4b126","entry":"make_image","repo":"kenjikawaguchi/qSGD","repo_kind":"official","path":"cifar10_WideResNet/utils/visualize.py","file_url":"https://github.com/kenjikawaguchi/qSGD/blob/HEAD/cifar10_WideResNet/utils/visualize.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":"1394422d51c4b126"}},{"code_sha256_prefix":"692b4557b97783d6","entry":"plot_overlap","repo":"kenjikawaguchi/qSGD","repo_kind":"official","path":"cifar10_WideResNet/utils/logger.py","file_url":"https://github.com/kenjikawaguchi/qSGD/blob/HEAD/cifar10_WideResNet/utils/logger.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":"692b4557b97783d6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}