{"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/regularizing-deep-neural-networks-with-1","title":"Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace","arxiv_id":"2208.05924","date":"2022-08-11","proceeding":null,"authors":["Yucong Liu","Shixing Yu","Tong Lin"],"abstract":"In this paper, we develop a novel regularization method for deep neural networks by penalizing the trace of Hessian. This regularizer is motivated by a recent guarantee bound of the generalization error. We explain its benefits in finding flat minima and avoiding Lyapunov stability in dynamical systems. We adopt the Hutchinson method as a classical unbiased estimator for the trace of a matrix and further accelerate its calculation using a dropout scheme. Experiments demonstrate that our method outperforms existing regularizers and data augmentation methods, such as Jacobian, Confidence Penalty, Label Smoothing, Cutout, and Mixup.","url_abs":"https://arxiv.org/abs/2208.05924v2","url_pdf":"https://arxiv.org/pdf/2208.05924v2.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":"regularizing-deep-neural-networks-with-1","repo_url":"https://github.com/iclrsubmission1596/regularizing-deep-neural-networks-with-stochastic-estimators-of-hessian-trace","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[{"method_slug":"cutout","method_name":"Cutout"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.05924","atlas_url":"https://app.syntology.ai/?focus=2208.05924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.05924"}},"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/iclrsubmission1596/regularizing-deep-neural-networks-with-stochastic-estimators-of-hessian-trace","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":5,"samples":[{"code_sha256_prefix":"c077f321f63362e6","entry":"batchify","repo":"iclrsubmission1596/regularizing-deep-neural-networks-with-stochastic-estimators-of-hessian-trace","repo_kind":"official","path":"WT2/wt2_lstm.py","file_url":"https://github.com/iclrsubmission1596/regularizing-deep-neural-networks-with-stochastic-estimators-of-hessian-trace/blob/HEAD/WT2/wt2_lstm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c077f321f63362e6"}},{"code_sha256_prefix":"00e569acd6b45ef0","entry":"conv3x3","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"00e569acd6b45ef0"}},{"code_sha256_prefix":"c8306d15070102aa","entry":"learning_rate","repo":"iclrsubmission1596/regularizing-deep-neural-networks-with-stochastic-estimators-of-hessian-trace","repo_kind":"official","path":"Cifar100/cifar_wide.py","file_url":"https://github.com/iclrsubmission1596/regularizing-deep-neural-networks-with-stochastic-estimators-of-hessian-trace/blob/HEAD/Cifar100/cifar_wide.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c8306d15070102aa"}},{"code_sha256_prefix":"a81c5fb0b9535995","entry":"repackage_hidden","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a81c5fb0b9535995"}},{"code_sha256_prefix":"71b00a6f0eb4b2b0","entry":"get_batch","repo":"iclrsubmission1596/regularizing-deep-neural-networks-with-stochastic-estimators-of-hessian-trace","repo_kind":"official","path":"WT2/wt2_lstm.py","file_url":"https://github.com/iclrsubmission1596/regularizing-deep-neural-networks-with-stochastic-estimators-of-hessian-trace/blob/HEAD/WT2/wt2_lstm.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":"71b00a6f0eb4b2b0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}