{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VXIYEIIQAM5AVMEBYFMUCFNIAU","short_pith_number":"pith:VXIYEIIQ","schema_version":"1.0","canonical_sha256":"add1822110033a0ab081c1594115a805146a8fe348b9d293659876f79dc53e7e","source":{"kind":"arxiv","id":"1812.05189","version":3},"attestation_state":"computed","paper":{"title":"Massively scalable Sinkhorn distances via the Nystr\\\"om method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Alessandro Rudi, Francis Bach, Jason Altschuler, Jonathan Niles-Weed","submitted_at":"2018-12-12T23:10:16Z","abstract_excerpt":"The Sinkhorn \"distance\", a variant of the Wasserstein distance with entropic regularization, is an increasingly popular tool in machine learning and statistical inference. However, the time and memory requirements of standard algorithms for computing this distance grow quadratically with the size of the data, making them prohibitively expensive on massive data sets. In this work, we show that this challenge is surprisingly easy to circumvent: combining two simple techniques---the Nystr\\\"om method and Sinkhorn scaling---provably yields an accurate approximation of the Sinkhorn distance with sig"},"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":"1812.05189","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-12T23:10:16Z","cross_cats_sorted":["cs.DS","cs.LG","math.OC"],"title_canon_sha256":"41f81002548c1563c1819cc7e369bdaab44659c2922e6186ba60ea935dd751fd","abstract_canon_sha256":"50903e3f5d79020ef427b5f21d8c1586f2213e6b7002596888a452d253449745"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:20.064605Z","signature_b64":"2+iUR2s6zloldeOBWcTWRf+ZFi/cQ6YJSA+KLTlRJtHzEyb3fENKEG/OqoYUZuNBRlH67KIybGUUUMjECBhJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"add1822110033a0ab081c1594115a805146a8fe348b9d293659876f79dc53e7e","last_reissued_at":"2026-07-05T03:31:20.064182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:20.064182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Massively scalable Sinkhorn distances via the Nystr\\\"om method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Alessandro Rudi, Francis Bach, Jason Altschuler, Jonathan Niles-Weed","submitted_at":"2018-12-12T23:10:16Z","abstract_excerpt":"The Sinkhorn \"distance\", a variant of the Wasserstein distance with entropic regularization, is an increasingly popular tool in machine learning and statistical inference. However, the time and memory requirements of standard algorithms for computing this distance grow quadratically with the size of the data, making them prohibitively expensive on massive data sets. In this work, we show that this challenge is surprisingly easy to circumvent: combining two simple techniques---the Nystr\\\"om method and Sinkhorn scaling---provably yields an accurate approximation of the Sinkhorn distance with sig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.05189","kind":"arxiv","version":3},"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/1812.05189/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":"1812.05189","created_at":"2026-07-05T03:31:20.064239+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.05189v3","created_at":"2026-07-05T03:31:20.064239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.05189","created_at":"2026-07-05T03:31:20.064239+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXIYEIIQAM5A","created_at":"2026-07-05T03:31:20.064239+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXIYEIIQAM5AVMEB","created_at":"2026-07-05T03:31:20.064239+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXIYEIIQ","created_at":"2026-07-05T03:31:20.064239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.20194","citing_title":"Coreset selection for the Sinkhorn divergence and generic smooth divergences","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXIYEIIQAM5AVMEBYFMUCFNIAU","json":"https://pith.science/pith/VXIYEIIQAM5AVMEBYFMUCFNIAU.json","graph_json":"https://pith.science/api/pith-number/VXIYEIIQAM5AVMEBYFMUCFNIAU/graph.json","events_json":"https://pith.science/api/pith-number/VXIYEIIQAM5AVMEBYFMUCFNIAU/events.json","paper":"https://pith.science/paper/VXIYEIIQ"},"agent_actions":{"view_html":"https://pith.science/pith/VXIYEIIQAM5AVMEBYFMUCFNIAU","download_json":"https://pith.science/pith/VXIYEIIQAM5AVMEBYFMUCFNIAU.json","view_paper":"https://pith.science/paper/VXIYEIIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.05189&json=true","fetch_graph":"https://pith.science/api/pith-number/VXIYEIIQAM5AVMEBYFMUCFNIAU/graph.json","fetch_events":"https://pith.science/api/pith-number/VXIYEIIQAM5AVMEBYFMUCFNIAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXIYEIIQAM5AVMEBYFMUCFNIAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXIYEIIQAM5AVMEBYFMUCFNIAU/action/storage_attestation","attest_author":"https://pith.science/pith/VXIYEIIQAM5AVMEBYFMUCFNIAU/action/author_attestation","sign_citation":"https://pith.science/pith/VXIYEIIQAM5AVMEBYFMUCFNIAU/action/citation_signature","submit_replication":"https://pith.science/pith/VXIYEIIQAM5AVMEBYFMUCFNIAU/action/replication_record"}},"created_at":"2026-07-05T03:31:20.064239+00:00","updated_at":"2026-07-05T03:31:20.064239+00:00"}