{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5Q5JBPFC3YNI3XA6C5DLBELFGP","short_pith_number":"pith:5Q5JBPFC","schema_version":"1.0","canonical_sha256":"ec3a90bca2de1a8ddc1e1746b0916533fe02398aa2e59f5f8781e99f5c93d53f","source":{"kind":"arxiv","id":"2101.01792","version":1},"attestation_state":"computed","paper":{"title":"Minibatch optimal transport distances; analysis and applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kilian Fatras, Nicolas Courty, R\\'emi Flamary, R\\'emi Gribonval, Szymon Majewski, Younes Zine","submitted_at":"2021-01-05T21:29:31Z","abstract_excerpt":"Optimal transport distances have become a classic tool to compare probability distributions and have found many applications in machine learning. Yet, despite recent algorithmic developments, their complexity prevents their direct use on large scale datasets. To overcome this challenge, a common workaround is to compute these distances on minibatches i.e. to average the outcome of several smaller optimal transport problems. We propose in this paper an extended analysis of this practice, which effects were previously studied in restricted cases. We first consider a large variety of Optimal Tran"},"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":"2101.01792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-01-05T21:29:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a0925eec935601f84c54f9d31491ebcb192a05d757247dcdedc2c87b9899cfc2","abstract_canon_sha256":"c8b9d8b03f3a14f33e8f415a1dd9a65d722586d6ee411de5901d5d0369acb8c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:00.366780Z","signature_b64":"jCZyS3bx8N5EuRdP6ZvOkD275hUbBzPG/cWUkRRrlTm8VA0Up2Sw76lb4p0rEAhp3mGWIQlgjI3yrJPM7QbNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec3a90bca2de1a8ddc1e1746b0916533fe02398aa2e59f5f8781e99f5c93d53f","last_reissued_at":"2026-07-05T02:05:00.366295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:00.366295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minibatch optimal transport distances; analysis and applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kilian Fatras, Nicolas Courty, R\\'emi Flamary, R\\'emi Gribonval, Szymon Majewski, Younes Zine","submitted_at":"2021-01-05T21:29:31Z","abstract_excerpt":"Optimal transport distances have become a classic tool to compare probability distributions and have found many applications in machine learning. Yet, despite recent algorithmic developments, their complexity prevents their direct use on large scale datasets. To overcome this challenge, a common workaround is to compute these distances on minibatches i.e. to average the outcome of several smaller optimal transport problems. We propose in this paper an extended analysis of this practice, which effects were previously studied in restricted cases. We first consider a large variety of Optimal Tran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01792","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/2101.01792/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":"2101.01792","created_at":"2026-07-05T02:05:00.366355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.01792v1","created_at":"2026-07-05T02:05:00.366355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01792","created_at":"2026-07-05T02:05:00.366355+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Q5JBPFC3YNI","created_at":"2026-07-05T02:05:00.366355+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Q5JBPFC3YNI3XA6","created_at":"2026-07-05T02:05:00.366355+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Q5JBPFC","created_at":"2026-07-05T02:05:00.366355+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02515","citing_title":"A Biconvex Formulation for Stable Transport of Mixture Models with a Unique Solution","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28075","citing_title":"Measure-to-measure Regression with Transformers","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28134","citing_title":"Convergence of empirical subgradients for optimal transport-based objectives","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30635","citing_title":"CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12174","citing_title":"Expected Batch Optimal Transport Plans and Consequences for Flow Matching","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07665","citing_title":"Debiased Counterfactual Generation via Flow Matching from Observations","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Q5JBPFC3YNI3XA6C5DLBELFGP","json":"https://pith.science/pith/5Q5JBPFC3YNI3XA6C5DLBELFGP.json","graph_json":"https://pith.science/api/pith-number/5Q5JBPFC3YNI3XA6C5DLBELFGP/graph.json","events_json":"https://pith.science/api/pith-number/5Q5JBPFC3YNI3XA6C5DLBELFGP/events.json","paper":"https://pith.science/paper/5Q5JBPFC"},"agent_actions":{"view_html":"https://pith.science/pith/5Q5JBPFC3YNI3XA6C5DLBELFGP","download_json":"https://pith.science/pith/5Q5JBPFC3YNI3XA6C5DLBELFGP.json","view_paper":"https://pith.science/paper/5Q5JBPFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.01792&json=true","fetch_graph":"https://pith.science/api/pith-number/5Q5JBPFC3YNI3XA6C5DLBELFGP/graph.json","fetch_events":"https://pith.science/api/pith-number/5Q5JBPFC3YNI3XA6C5DLBELFGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Q5JBPFC3YNI3XA6C5DLBELFGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Q5JBPFC3YNI3XA6C5DLBELFGP/action/storage_attestation","attest_author":"https://pith.science/pith/5Q5JBPFC3YNI3XA6C5DLBELFGP/action/author_attestation","sign_citation":"https://pith.science/pith/5Q5JBPFC3YNI3XA6C5DLBELFGP/action/citation_signature","submit_replication":"https://pith.science/pith/5Q5JBPFC3YNI3XA6C5DLBELFGP/action/replication_record"}},"created_at":"2026-07-05T02:05:00.366355+00:00","updated_at":"2026-07-05T02:05:00.366355+00:00"}