{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RA3MZQ2Y6T4HYXWFIAYBQ2WGCO","short_pith_number":"pith:RA3MZQ2Y","schema_version":"1.0","canonical_sha256":"8836ccc358f4f87c5ec54030186ac61397d6c83953cf0cab980d930c14f0e572","source":{"kind":"arxiv","id":"1909.06918","version":1},"attestation_state":"computed","paper":{"title":"Sinkhorn Algorithm as a Special Case of Stochastic Mirror Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Konstantin Mishchenko","submitted_at":"2019-09-16T00:58:17Z","abstract_excerpt":"We present a new perspective on the celebrated Sinkhorn algorithm by showing that is a special case of incremental/stochastic mirror descent. In order to see this, one should simply plug Kullback-Leibler divergence in both mirror map and the objective function. Since the problem has unbounded domain, the objective function is neither smooth nor it has bounded gradients. However, one can still approach the problem using the notion of relative smoothness, obtaining that the stochastic objective is 1-relative smooth. The discovered equivalence allows us to propose 1) new methods for optimal trans"},"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":"1909.06918","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-16T00:58:17Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"f3c9ec1b5d8b89dd33e67a4a1c259f5cac809ce43d3a7a44a17c3330ab8d3bef","abstract_canon_sha256":"ad7fc6866b952185a97f5db05a6ddf52addd659195a1b6ff3249b18e7c5d1063"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:51.410278Z","signature_b64":"xoLxvlQeIB/hLyaIR3BuBNmDXt8IQV2a+iT3o4TQkLWUO5ZSZQNlWhPE+LqSGlEGIsQUfBYksnTDytcLtYPYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8836ccc358f4f87c5ec54030186ac61397d6c83953cf0cab980d930c14f0e572","last_reissued_at":"2026-07-05T00:04:51.409940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:51.409940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sinkhorn Algorithm as a Special Case of Stochastic Mirror Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Konstantin Mishchenko","submitted_at":"2019-09-16T00:58:17Z","abstract_excerpt":"We present a new perspective on the celebrated Sinkhorn algorithm by showing that is a special case of incremental/stochastic mirror descent. In order to see this, one should simply plug Kullback-Leibler divergence in both mirror map and the objective function. Since the problem has unbounded domain, the objective function is neither smooth nor it has bounded gradients. However, one can still approach the problem using the notion of relative smoothness, obtaining that the stochastic objective is 1-relative smooth. The discovered equivalence allows us to propose 1) new methods for optimal trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06918","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/1909.06918/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":"1909.06918","created_at":"2026-07-05T00:04:51.409996+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.06918v1","created_at":"2026-07-05T00:04:51.409996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06918","created_at":"2026-07-05T00:04:51.409996+00:00"},{"alias_kind":"pith_short_12","alias_value":"RA3MZQ2Y6T4H","created_at":"2026-07-05T00:04:51.409996+00:00"},{"alias_kind":"pith_short_16","alias_value":"RA3MZQ2Y6T4HYXWF","created_at":"2026-07-05T00:04:51.409996+00:00"},{"alias_kind":"pith_short_8","alias_value":"RA3MZQ2Y","created_at":"2026-07-05T00:04:51.409996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11513","citing_title":"Nonlocal Onsager Operators and Entropy Dissipation for Finite-State Schr\\\"odinger Bridges","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00665","citing_title":"Effective dynamics of the Sinkhorn algorithm in the regime of low entropy regularization","ref_index":68,"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":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30267","citing_title":"Accelerating Sinkhorn for Entropy-Regularized Optimal Transport","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO","json":"https://pith.science/pith/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO.json","graph_json":"https://pith.science/api/pith-number/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO/graph.json","events_json":"https://pith.science/api/pith-number/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO/events.json","paper":"https://pith.science/paper/RA3MZQ2Y"},"agent_actions":{"view_html":"https://pith.science/pith/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO","download_json":"https://pith.science/pith/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO.json","view_paper":"https://pith.science/paper/RA3MZQ2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.06918&json=true","fetch_graph":"https://pith.science/api/pith-number/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO/graph.json","fetch_events":"https://pith.science/api/pith-number/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO/action/storage_attestation","attest_author":"https://pith.science/pith/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO/action/author_attestation","sign_citation":"https://pith.science/pith/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO/action/citation_signature","submit_replication":"https://pith.science/pith/RA3MZQ2Y6T4HYXWFIAYBQ2WGCO/action/replication_record"}},"created_at":"2026-07-05T00:04:51.409996+00:00","updated_at":"2026-07-05T00:04:51.409996+00:00"}