{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:G54QL73JIGEZK34QH6TGDLNJ4Z","short_pith_number":"pith:G54QL73J","schema_version":"1.0","canonical_sha256":"377905ff694189956f903fa661ada9e667fff7036251ffc7d85d2062b497c402","source":{"kind":"arxiv","id":"2006.08172","version":2},"attestation_state":"computed","paper":{"title":"Faster Wasserstein Distance Estimation with the Sinkhorn Divergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"math.OC","authors_text":"Flavien L\\'eger (DMA), Fran\\c{c}ois-Xavier Vialard (Univ Gustave Eiffel), Gabriel Peyr\\'e (DMA), Lenaic Chizat (LMO), Pierre Roussillon (DMA)","submitted_at":"2020-06-15T06:58:16Z","abstract_excerpt":"The squared Wasserstein distance is a natural quantity to compare probability distributions in a non-parametric setting. This quantity is usually estimated with the plug-in estimator, defined via a discrete optimal transport problem which can be solved to $\\epsilon$-accuracy by adding an entropic regularization of order $\\epsilon$ and using for instance Sinkhorn's algorithm. In this work, we propose instead to estimate it with the Sinkhorn divergence, which is also built on entropic regularization but includes debiasing terms. We show that, for smooth densities, this estimator has a comparable"},"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":"2006.08172","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-15T06:58:16Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"f8a1bcef909bcbbf575a390a8a7f6e2e2b1873126b15f36b6b18c966cbfd37f5","abstract_canon_sha256":"c3918bf3a83c5128f435966f45a9dc471816e2f52db90bf65a8fd9b0cc7ae6e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:31.186906Z","signature_b64":"DkXL66PAgEHnhSo6cDLOeNJfktbgDkDeRACz+NQblWm05fdyuwabP5Uj9WoBsgJPUgLXOoe8Bo95Fe1dt1axBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"377905ff694189956f903fa661ada9e667fff7036251ffc7d85d2062b497c402","last_reissued_at":"2026-07-05T01:47:31.186552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:31.186552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faster Wasserstein Distance Estimation with the Sinkhorn Divergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"math.OC","authors_text":"Flavien L\\'eger (DMA), Fran\\c{c}ois-Xavier Vialard (Univ Gustave Eiffel), Gabriel Peyr\\'e (DMA), Lenaic Chizat (LMO), Pierre Roussillon (DMA)","submitted_at":"2020-06-15T06:58:16Z","abstract_excerpt":"The squared Wasserstein distance is a natural quantity to compare probability distributions in a non-parametric setting. This quantity is usually estimated with the plug-in estimator, defined via a discrete optimal transport problem which can be solved to $\\epsilon$-accuracy by adding an entropic regularization of order $\\epsilon$ and using for instance Sinkhorn's algorithm. In this work, we propose instead to estimate it with the Sinkhorn divergence, which is also built on entropic regularization but includes debiasing terms. We show that, for smooth densities, this estimator has a comparable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08172","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/2006.08172/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":"2006.08172","created_at":"2026-07-05T01:47:31.186612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.08172v2","created_at":"2026-07-05T01:47:31.186612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08172","created_at":"2026-07-05T01:47:31.186612+00:00"},{"alias_kind":"pith_short_12","alias_value":"G54QL73JIGEZ","created_at":"2026-07-05T01:47:31.186612+00:00"},{"alias_kind":"pith_short_16","alias_value":"G54QL73JIGEZK34Q","created_at":"2026-07-05T01:47:31.186612+00:00"},{"alias_kind":"pith_short_8","alias_value":"G54QL73J","created_at":"2026-07-05T01:47:31.186612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22670","citing_title":"Curvature of optimal transport with respect to the cost and applications to inverse optimal transport","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G54QL73JIGEZK34QH6TGDLNJ4Z","json":"https://pith.science/pith/G54QL73JIGEZK34QH6TGDLNJ4Z.json","graph_json":"https://pith.science/api/pith-number/G54QL73JIGEZK34QH6TGDLNJ4Z/graph.json","events_json":"https://pith.science/api/pith-number/G54QL73JIGEZK34QH6TGDLNJ4Z/events.json","paper":"https://pith.science/paper/G54QL73J"},"agent_actions":{"view_html":"https://pith.science/pith/G54QL73JIGEZK34QH6TGDLNJ4Z","download_json":"https://pith.science/pith/G54QL73JIGEZK34QH6TGDLNJ4Z.json","view_paper":"https://pith.science/paper/G54QL73J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.08172&json=true","fetch_graph":"https://pith.science/api/pith-number/G54QL73JIGEZK34QH6TGDLNJ4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/G54QL73JIGEZK34QH6TGDLNJ4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G54QL73JIGEZK34QH6TGDLNJ4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G54QL73JIGEZK34QH6TGDLNJ4Z/action/storage_attestation","attest_author":"https://pith.science/pith/G54QL73JIGEZK34QH6TGDLNJ4Z/action/author_attestation","sign_citation":"https://pith.science/pith/G54QL73JIGEZK34QH6TGDLNJ4Z/action/citation_signature","submit_replication":"https://pith.science/pith/G54QL73JIGEZK34QH6TGDLNJ4Z/action/replication_record"}},"created_at":"2026-07-05T01:47:31.186612+00:00","updated_at":"2026-07-05T01:47:31.186612+00:00"}