{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FZXRDHEFX5CVU4YONP6EI2NASK","short_pith_number":"pith:FZXRDHEF","schema_version":"1.0","canonical_sha256":"2e6f119c85bf455a730e6bfc4469a0929ea5d417bb5da72176ecb9814ed86957","source":{"kind":"arxiv","id":"1810.02733","version":2},"attestation_state":"computed","paper":{"title":"Sample Complexity of Sinkhorn divergences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Aude Genevay, Francis Bach, Gabriel Peyr\\'e, L\\'enaic Chizat, Marco Cuturi","submitted_at":"2018-10-05T14:55:05Z","abstract_excerpt":"Optimal transport (OT) and maximum mean discrepancies (MMD) are now routinely used in machine learning to compare probability measures. We focus in this paper on \\emph{Sinkhorn divergences} (SDs), a regularized variant of OT distances which can interpolate, depending on the regularization strength $\\varepsilon$, between OT ($\\varepsilon=0$) and MMD ($\\varepsilon=\\infty$). Although the tradeoff induced by that regularization is now well understood computationally (OT, SDs and MMD require respectively $O(n^3\\log n)$, $O(n^2)$ and $n^2$ operations given a sample size $n$), much less is known in t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1810.02733","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-10-05T14:55:05Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"bf63cfa7c15ffb8c29c802c8f5e8787b263eab4199d85f109ce2d4501c06cc19","abstract_canon_sha256":"4bcb922000a993c92f8ed3b639f0bef12c3f0617ad25723ff15565fa0d548a6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:46.187357Z","signature_b64":"6/wP9hG1yqgEEpozKwEPhU0xwnHS8ucDLfa80HeEt80xGs2LkaecVy3o26dimXMebpJD494m2NG06anJLhWJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e6f119c85bf455a730e6bfc4469a0929ea5d417bb5da72176ecb9814ed86957","last_reissued_at":"2026-07-05T00:11:46.186887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:46.186887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample Complexity of Sinkhorn divergences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Aude Genevay, Francis Bach, Gabriel Peyr\\'e, L\\'enaic Chizat, Marco Cuturi","submitted_at":"2018-10-05T14:55:05Z","abstract_excerpt":"Optimal transport (OT) and maximum mean discrepancies (MMD) are now routinely used in machine learning to compare probability measures. We focus in this paper on \\emph{Sinkhorn divergences} (SDs), a regularized variant of OT distances which can interpolate, depending on the regularization strength $\\varepsilon$, between OT ($\\varepsilon=0$) and MMD ($\\varepsilon=\\infty$). Although the tradeoff induced by that regularization is now well understood computationally (OT, SDs and MMD require respectively $O(n^3\\log n)$, $O(n^2)$ and $n^2$ operations given a sample size $n$), much less is known in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02733","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1810.02733/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1810.02733","created_at":"2026-07-05T00:11:46.186940+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.02733v2","created_at":"2026-07-05T00:11:46.186940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02733","created_at":"2026-07-05T00:11:46.186940+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZXRDHEFX5CV","created_at":"2026-07-05T00:11:46.186940+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZXRDHEFX5CVU4YO","created_at":"2026-07-05T00:11:46.186940+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZXRDHEF","created_at":"2026-07-05T00:11:46.186940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08485","citing_title":"Sinkhorn Treatment Effects: A Causal Optimal Transport Measure","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZXRDHEFX5CVU4YONP6EI2NASK","json":"https://pith.science/pith/FZXRDHEFX5CVU4YONP6EI2NASK.json","graph_json":"https://pith.science/api/pith-number/FZXRDHEFX5CVU4YONP6EI2NASK/graph.json","events_json":"https://pith.science/api/pith-number/FZXRDHEFX5CVU4YONP6EI2NASK/events.json","paper":"https://pith.science/paper/FZXRDHEF"},"agent_actions":{"view_html":"https://pith.science/pith/FZXRDHEFX5CVU4YONP6EI2NASK","download_json":"https://pith.science/pith/FZXRDHEFX5CVU4YONP6EI2NASK.json","view_paper":"https://pith.science/paper/FZXRDHEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.02733&json=true","fetch_graph":"https://pith.science/api/pith-number/FZXRDHEFX5CVU4YONP6EI2NASK/graph.json","fetch_events":"https://pith.science/api/pith-number/FZXRDHEFX5CVU4YONP6EI2NASK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZXRDHEFX5CVU4YONP6EI2NASK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZXRDHEFX5CVU4YONP6EI2NASK/action/storage_attestation","attest_author":"https://pith.science/pith/FZXRDHEFX5CVU4YONP6EI2NASK/action/author_attestation","sign_citation":"https://pith.science/pith/FZXRDHEFX5CVU4YONP6EI2NASK/action/citation_signature","submit_replication":"https://pith.science/pith/FZXRDHEFX5CVU4YONP6EI2NASK/action/replication_record"}},"created_at":"2026-07-05T00:11:46.186940+00:00","updated_at":"2026-07-05T00:11:46.186940+00:00"}