{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YSU4MG6YSGPTYQX75BDM4D4OLB","short_pith_number":"pith:YSU4MG6Y","schema_version":"1.0","canonical_sha256":"c4a9c61bd8919f3c42ffe846ce0f8e586be04ed2ae9ca96ad9fdf698e06c0b16","source":{"kind":"arxiv","id":"2401.12253","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Sinkhorn Algorithm with Sparse Newton Iterations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Elisa Tardini, Holakou Rahmanian, Kiran Koshy Thekumparampil, Lexing Ying, Michael Shavlovsky, Tesi Xiao, Xun Tang","submitted_at":"2024-01-20T21:23:09Z","abstract_excerpt":"Computing the optimal transport distance between statistical distributions is a fundamental task in machine learning. One remarkable recent advancement is entropic regularization and the Sinkhorn algorithm, which utilizes only matrix scaling and guarantees an approximated solution with near-linear runtime. Despite the success of the Sinkhorn algorithm, its runtime may still be slow due to the potentially large number of iterations needed for convergence. To achieve possibly super-exponential convergence, we present Sinkhorn-Newton-Sparse (SNS), an extension to the Sinkhorn algorithm, by introd"},"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":"2401.12253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-01-20T21:23:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"942dcb9aa1c2914ba796ab2173be48bd570fb585825c58722a0f8a13dea9b773","abstract_canon_sha256":"7e7e547e6c48d3d59ea4565b510c1bd44683f05a0a8e04daebfdeff8732b3ab6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:28.071239Z","signature_b64":"afIW5xe/SJ5df6/582VQNvqusJQZZmDJ/5vF8YglVsW62HrZudylNbZKUlgxC0TeuQl151Ss/ZXQHFQFEyt8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4a9c61bd8919f3c42ffe846ce0f8e586be04ed2ae9ca96ad9fdf698e06c0b16","last_reissued_at":"2026-07-05T07:36:28.070864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:28.070864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Sinkhorn Algorithm with Sparse Newton Iterations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Elisa Tardini, Holakou Rahmanian, Kiran Koshy Thekumparampil, Lexing Ying, Michael Shavlovsky, Tesi Xiao, Xun Tang","submitted_at":"2024-01-20T21:23:09Z","abstract_excerpt":"Computing the optimal transport distance between statistical distributions is a fundamental task in machine learning. One remarkable recent advancement is entropic regularization and the Sinkhorn algorithm, which utilizes only matrix scaling and guarantees an approximated solution with near-linear runtime. Despite the success of the Sinkhorn algorithm, its runtime may still be slow due to the potentially large number of iterations needed for convergence. To achieve possibly super-exponential convergence, we present Sinkhorn-Newton-Sparse (SNS), an extension to the Sinkhorn algorithm, by introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12253","kind":"arxiv","version":1},"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/2401.12253/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":"2401.12253","created_at":"2026-07-05T07:36:28.070915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12253v1","created_at":"2026-07-05T07:36:28.070915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12253","created_at":"2026-07-05T07:36:28.070915+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSU4MG6YSGPT","created_at":"2026-07-05T07:36:28.070915+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSU4MG6YSGPTYQX7","created_at":"2026-07-05T07:36:28.070915+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSU4MG6Y","created_at":"2026-07-05T07:36:28.070915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08104","citing_title":"APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSU4MG6YSGPTYQX75BDM4D4OLB","json":"https://pith.science/pith/YSU4MG6YSGPTYQX75BDM4D4OLB.json","graph_json":"https://pith.science/api/pith-number/YSU4MG6YSGPTYQX75BDM4D4OLB/graph.json","events_json":"https://pith.science/api/pith-number/YSU4MG6YSGPTYQX75BDM4D4OLB/events.json","paper":"https://pith.science/paper/YSU4MG6Y"},"agent_actions":{"view_html":"https://pith.science/pith/YSU4MG6YSGPTYQX75BDM4D4OLB","download_json":"https://pith.science/pith/YSU4MG6YSGPTYQX75BDM4D4OLB.json","view_paper":"https://pith.science/paper/YSU4MG6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12253&json=true","fetch_graph":"https://pith.science/api/pith-number/YSU4MG6YSGPTYQX75BDM4D4OLB/graph.json","fetch_events":"https://pith.science/api/pith-number/YSU4MG6YSGPTYQX75BDM4D4OLB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSU4MG6YSGPTYQX75BDM4D4OLB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSU4MG6YSGPTYQX75BDM4D4OLB/action/storage_attestation","attest_author":"https://pith.science/pith/YSU4MG6YSGPTYQX75BDM4D4OLB/action/author_attestation","sign_citation":"https://pith.science/pith/YSU4MG6YSGPTYQX75BDM4D4OLB/action/citation_signature","submit_replication":"https://pith.science/pith/YSU4MG6YSGPTYQX75BDM4D4OLB/action/replication_record"}},"created_at":"2026-07-05T07:36:28.070915+00:00","updated_at":"2026-07-05T07:36:28.070915+00:00"}