{"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/181008278","title":"Interpolating between Optimal Transport and MMD using Sinkhorn Divergences","arxiv_id":"1810.08278","date":"2018-10-18","proceeding":null,"authors":["Jean Feydy","Thibault Séjourné","François-Xavier Vialard","Shun-ichi Amari","Alain Trouvé","Gabriel Peyré"],"abstract":"Comparing probability distributions is a fundamental problem in data sciences. Simple norms and divergences such as the total variation and the relative entropy only compare densities in a point-wise manner and fail to capture the geometric nature of the problem. In sharp contrast, Maximum Mean Discrepancies (MMD) and Optimal Transport distances (OT) are two classes of distances between measures that take into account the geometry of the underlying space and metrize the convergence in law. This paper studies the Sinkhorn divergences, a family of geometric divergences that interpolates between MMD and OT. Relying on a new notion of geometric entropy, we provide theoretical guarantees for these divergences: positivity, convexity and metrization of the convergence in law. On the practical side, we detail a numerical scheme that enables the large scale application of these divergences for machine learning: on the GPU, gradients of the Sinkhorn loss can be computed for batches of a million samples.","url_abs":"http://arxiv.org/abs/1810.08278v1","url_pdf":"http://arxiv.org/pdf/1810.08278v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"181008278","repo_url":"https://github.com/jeanfeydy/global-divergences","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.08278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.08278"}},"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/jeanfeydy/global-divergences","reach":null}],"summary":{"ran_honours":2,"unverified":2},"by_repo_kind":{"official":{"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":"2de9422f97b91419","entry":"lse","repo":"jeanfeydy/global-divergences","repo_kind":"official","path":"common/sinkhorn_balanced.py","file_url":"https://github.com/jeanfeydy/global-divergences/blob/HEAD/common/sinkhorn_balanced.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":"2de9422f97b91419"}},{"code_sha256_prefix":"c479e6772a64ac69","entry":"scal","repo":"jeanfeydy/global-divergences","repo_kind":"official","path":"common/sinkhorn_balanced.py","file_url":"https://github.com/jeanfeydy/global-divergences/blob/HEAD/common/sinkhorn_balanced.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":"c479e6772a64ac69"}},{"code_sha256_prefix":"ee384b6a828faf95","entry":"LoadImage","repo":"jeanfeydy/global-divergences","repo_kind":"official","path":"global_divergences_ShapeMI2018/demo_2D.py","file_url":"https://github.com/jeanfeydy/global-divergences/blob/HEAD/global_divergences_ShapeMI2018/demo_2D.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":"ee384b6a828faf95"}},{"code_sha256_prefix":"18e0065bfe72ae2f","entry":"Sinkhorn_ops","repo":"jeanfeydy/global-divergences","repo_kind":"official","path":"common/sinkhorn_balanced.py","file_url":"https://github.com/jeanfeydy/global-divergences/blob/HEAD/common/sinkhorn_balanced.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":"18e0065bfe72ae2f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}