{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3HCZLQV5FFIBJ73PZUWKGBHX4I","short_pith_number":"pith:3HCZLQV5","schema_version":"1.0","canonical_sha256":"d9c595c2bd295014ff6fcd2ca304f7e2362a3020429201ebaaec048536e951b9","source":{"kind":"arxiv","id":"2408.11620","version":1},"attestation_state":"computed","paper":{"title":"Annealed Sinkhorn for Optimal Transport: convergence, regularization path and debiasing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"L\\'ena\\\"ic Chizat","submitted_at":"2024-08-21T13:47:01Z","abstract_excerpt":"Sinkhorn's algorithm is a method of choice to solve large-scale optimal transport (OT) problems. In this context, it involves an inverse temperature parameter $\\beta$ that determines the speed-accuracy trade-off. To improve this trade-off, practitioners often use a variant of this algorithm, Annealed Sinkhorn, that uses an nondecreasing sequence $(\\beta_t)_{t\\in \\mathbb{N}}$ where $t$ is the iteration count. However, besides for the schedule $\\beta_t=\\Theta(\\log t)$ which is impractically slow, it is not known whether this variant is guaranteed to actually solve OT. Our first contribution answ"},"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":"2408.11620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-21T13:47:01Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"d1558a79830c9f47fd51d5871910489aeb3b4d35427f05dbb308a3ca2f90629a","abstract_canon_sha256":"4087e6f1328bf891b9f1994eff25fa048185d940922d75a9309088149ee88814"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:46.161065Z","signature_b64":"WzyZ1+zNBAqd/K63XwbPbF5i+FI90oX4F3O/hQFlAW34w3YrfLt772p06j61g/jJMS4lsgR2SyLnqORGRh9TCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9c595c2bd295014ff6fcd2ca304f7e2362a3020429201ebaaec048536e951b9","last_reissued_at":"2026-07-05T08:57:46.160557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:46.160557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Annealed Sinkhorn for Optimal Transport: convergence, regularization path and debiasing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"L\\'ena\\\"ic Chizat","submitted_at":"2024-08-21T13:47:01Z","abstract_excerpt":"Sinkhorn's algorithm is a method of choice to solve large-scale optimal transport (OT) problems. In this context, it involves an inverse temperature parameter $\\beta$ that determines the speed-accuracy trade-off. To improve this trade-off, practitioners often use a variant of this algorithm, Annealed Sinkhorn, that uses an nondecreasing sequence $(\\beta_t)_{t\\in \\mathbb{N}}$ where $t$ is the iteration count. However, besides for the schedule $\\beta_t=\\Theta(\\log t)$ which is impractically slow, it is not known whether this variant is guaranteed to actually solve OT. Our first contribution answ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11620","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/2408.11620/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":"2408.11620","created_at":"2026-07-05T08:57:46.160623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11620v1","created_at":"2026-07-05T08:57:46.160623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11620","created_at":"2026-07-05T08:57:46.160623+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HCZLQV5FFIB","created_at":"2026-07-05T08:57:46.160623+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HCZLQV5FFIBJ73P","created_at":"2026-07-05T08:57:46.160623+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HCZLQV5","created_at":"2026-07-05T08:57:46.160623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00665","citing_title":"Effective dynamics of the Sinkhorn algorithm in the regime of low entropy regularization","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28973","citing_title":"Sharp $O(1/k)$ convergence rate for the Sinkhorn algorithm via a local analysis","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25551","citing_title":"Learning Permutation from Structure Without Supervision","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30267","citing_title":"Accelerating Sinkhorn for Entropy-Regularized Optimal Transport","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HCZLQV5FFIBJ73PZUWKGBHX4I","json":"https://pith.science/pith/3HCZLQV5FFIBJ73PZUWKGBHX4I.json","graph_json":"https://pith.science/api/pith-number/3HCZLQV5FFIBJ73PZUWKGBHX4I/graph.json","events_json":"https://pith.science/api/pith-number/3HCZLQV5FFIBJ73PZUWKGBHX4I/events.json","paper":"https://pith.science/paper/3HCZLQV5"},"agent_actions":{"view_html":"https://pith.science/pith/3HCZLQV5FFIBJ73PZUWKGBHX4I","download_json":"https://pith.science/pith/3HCZLQV5FFIBJ73PZUWKGBHX4I.json","view_paper":"https://pith.science/paper/3HCZLQV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11620&json=true","fetch_graph":"https://pith.science/api/pith-number/3HCZLQV5FFIBJ73PZUWKGBHX4I/graph.json","fetch_events":"https://pith.science/api/pith-number/3HCZLQV5FFIBJ73PZUWKGBHX4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HCZLQV5FFIBJ73PZUWKGBHX4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HCZLQV5FFIBJ73PZUWKGBHX4I/action/storage_attestation","attest_author":"https://pith.science/pith/3HCZLQV5FFIBJ73PZUWKGBHX4I/action/author_attestation","sign_citation":"https://pith.science/pith/3HCZLQV5FFIBJ73PZUWKGBHX4I/action/citation_signature","submit_replication":"https://pith.science/pith/3HCZLQV5FFIBJ73PZUWKGBHX4I/action/replication_record"}},"created_at":"2026-07-05T08:57:46.160623+00:00","updated_at":"2026-07-05T08:57:46.160623+00:00"}