{"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/measuring-generalization-with-optimal","title":"Measuring Generalization with Optimal Transport","arxiv_id":"2106.03314","date":"2021-06-07","proceeding":"NeurIPS 2021 12","authors":["Ching-Yao Chuang","Youssef Mroueh","Kristjan Greenewald","Antonio Torralba","Stefanie Jegelka"],"abstract":"Understanding the generalization of deep neural networks is one of the most important tasks in deep learning. Although much progress has been made, theoretical error bounds still often behave disparately from empirical observations. In this work, we develop margin-based generalization bounds, where the margins are normalized with optimal transport costs between independent random subsets sampled from the training distribution. In particular, the optimal transport cost can be interpreted as a generalization of variance which captures the structural properties of the learned feature space. Our bounds robustly predict the generalization error, given training data and network parameters, on large scale datasets. Theoretically, we demonstrate that the concentration and separation of features play crucial roles in generalization, supporting empirical results in the literature. The code is available at \\url{https://github.com/chingyaoc/kV-Margin}.","url_abs":"https://arxiv.org/abs/2106.03314v2","url_pdf":"https://arxiv.org/pdf/2106.03314v2.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":"measuring-generalization-with-optimal","repo_url":"https://github.com/chingyaoc/kV-Margin","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"generalization-bounds","task_name":"Generalization Bounds"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.03314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03314"}},"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/google-research/google-research","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/chingyaoc/kV-Margin","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/pluskid/fitting-random-labels","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"found_in_text":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"26f889590f355fa1","entry":"W1_distance","repo":"chingyaoc/kV-Margin","repo_kind":"official","path":"kV-Margin/complexity.py","file_url":"https://github.com/chingyaoc/kV-Margin/blob/HEAD/kV-Margin/complexity.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26f889590f355fa1"}},{"code_sha256_prefix":"8f9d0ec380238d28","entry":"get_norm_fn","repo":"google-research/google-research","repo_kind":"found_in_text","path":"large_margin/margin_loss.py","file_url":"https://github.com/google-research/google-research/blob/HEAD/large_margin/margin_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8f9d0ec380238d28"}},{"code_sha256_prefix":"3f5c11b768870046","entry":"margin_loss","repo":"chingyaoc/kv-margin","repo_kind":"official","path":"kV-Margin/complexity.py","file_url":"https://github.com/chingyaoc/kv-margin/blob/HEAD/kV-Margin/complexity.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f5c11b768870046"}},{"code_sha256_prefix":"8f104337b1314ff5","entry":"maximum_with_relu","repo":"google-research/google-research","repo_kind":"found_in_text","path":"large_margin/margin_loss.py","file_url":"https://github.com/google-research/google-research/blob/HEAD/large_margin/margin_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8f104337b1314ff5"}},{"code_sha256_prefix":"c6e67c0b195574c8","entry":"_ensure_large_margin_args","repo":"google-research/google-research","repo_kind":"found_in_text","path":"large_margin/margin_loss.py","file_url":"https://github.com/google-research/google-research/blob/HEAD/large_margin/margin_loss.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":"c6e67c0b195574c8"}},{"code_sha256_prefix":"62970767d2137041","entry":"large_margin","repo":"google-research/google-research","repo_kind":"found_in_text","path":"large_margin/margin_loss.py","file_url":"https://github.com/google-research/google-research/blob/HEAD/large_margin/margin_loss.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":"62970767d2137041"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}