{"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/information-theoretic-local-minima-1","title":"Information-Theoretic Local Minima Characterization and Regularization","arxiv_id":"1911.08192","date":"2019-11-19","proceeding":"ICML 2020 1","authors":["Zhiwei Jia","Hao Su"],"abstract":"Recent advances in deep learning theory have evoked the study of generalizability across different local minima of deep neural networks (DNNs). While current work focused on either discovering properties of good local minima or developing regularization techniques to induce good local minima, no approach exists that can tackle both problems. We achieve these two goals successfully in a unified manner. Specifically, based on the observed Fisher information we propose a metric both strongly indicative of generalizability of local minima and effectively applied as a practical regularizer. We provide theoretical analysis including a generalization bound and empirically demonstrate the success of our approach in both capturing and improving the generalizability of DNNs. Experiments are performed on CIFAR-10, CIFAR-100 and ImageNet for various network architectures.","url_abs":"https://arxiv.org/abs/1911.08192v2","url_pdf":"https://arxiv.org/pdf/1911.08192v2.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":"information-theoretic-local-minima-1","repo_url":"https://github.com/SeanJia/InfoMCR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"learning-theory","task_name":"Learning Theory"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1911.08192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08192"}},"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/SeanJia/InfoMCR","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"a0c42b3464544bef","entry":"compute_gamma","repo":"SeanJia/InfoMCR","repo_kind":"official","path":"src/eval_cifar10.py","file_url":"https://github.com/SeanJia/InfoMCR/blob/HEAD/src/eval_cifar10.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":"a0c42b3464544bef"}},{"code_sha256_prefix":"f966d60059497fde","entry":"compute_logsum","repo":"SeanJia/InfoMCR","repo_kind":"official","path":"src/eval_cifar10.py","file_url":"https://github.com/SeanJia/InfoMCR/blob/HEAD/src/eval_cifar10.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":"f966d60059497fde"}},{"code_sha256_prefix":"cc9c2631fdfad77e","entry":"get_summary_writer","repo":"SeanJia/InfoMCR","repo_kind":"official","path":"src/train_cifar10.py","file_url":"https://github.com/SeanJia/InfoMCR/blob/HEAD/src/train_cifar10.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":"cc9c2631fdfad77e"}},{"code_sha256_prefix":"1217c6df0212451f","entry":"learning_rate_schedule","repo":"SeanJia/InfoMCR","repo_kind":"official","path":"src/train_cifar10.py","file_url":"https://github.com/SeanJia/InfoMCR/blob/HEAD/src/train_cifar10.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":"1217c6df0212451f"}},{"code_sha256_prefix":"5d91de9f6dbf98d9","entry":"make_residual_block","repo":"SeanJia/InfoMCR","repo_kind":"official","path":"src/wide_resnet/residual_block.py","file_url":"https://github.com/SeanJia/InfoMCR/blob/HEAD/src/wide_resnet/residual_block.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":"5d91de9f6dbf98d9"}},{"code_sha256_prefix":"e3044e542c409000","entry":"wide_resnet_28_2","repo":"SeanJia/InfoMCR","repo_kind":"official","path":"src/wide_resnet/wide_resnet.py","file_url":"https://github.com/SeanJia/InfoMCR/blob/HEAD/src/wide_resnet/wide_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":"e3044e542c409000"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}