{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JXU6T446GI5MLODAN7NYR6IETQ","short_pith_number":"pith:JXU6T446","schema_version":"1.0","canonical_sha256":"4de9e9f39e323ac5b8606fdb88f9049c3773d9bb13b9add66ac7077c9ec43ca3","source":{"kind":"arxiv","id":"1908.10962","version":2},"attestation_state":"computed","paper":{"title":"Optimal transport mapping via input convex neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amirhossein Taghvaei, Ashok Vardhan Makkuva, Jason D. Lee, Sewoong Oh","submitted_at":"2019-08-28T21:59:58Z","abstract_excerpt":"In this paper, we present a novel and principled approach to learn the optimal transport between two distributions, from samples. Guided by the optimal transport theory, we learn the optimal Kantorovich potential which induces the optimal transport map. This involves learning two convex functions, by solving a novel minimax optimization. Building upon recent advances in the field of input convex neural networks, we propose a new framework where the gradient of one convex function represents the optimal transport mapping. Numerical experiments confirm that we learn the optimal transport mapping"},"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":"1908.10962","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-08-28T21:59:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"75b94ba6a46702fd3ddbbc45b28df277a6454679306d466b4febb78ac25723d0","abstract_canon_sha256":"b1686d9b0b9a275427376d96a37d0c5d8fdd1475eed96dede8b32f2f688c9548"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:09.865455Z","signature_b64":"B+e3GsgfiVnADPnNp+gullXkaM92ng+fE+IZ4kztsI19kyYZ1FBPaNK7byOVfwlWfGGV7kb0w35ZK5EUBcVGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4de9e9f39e323ac5b8606fdb88f9049c3773d9bb13b9add66ac7077c9ec43ca3","last_reissued_at":"2026-07-05T01:11:09.864957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:09.864957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal transport mapping via input convex neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amirhossein Taghvaei, Ashok Vardhan Makkuva, Jason D. Lee, Sewoong Oh","submitted_at":"2019-08-28T21:59:58Z","abstract_excerpt":"In this paper, we present a novel and principled approach to learn the optimal transport between two distributions, from samples. Guided by the optimal transport theory, we learn the optimal Kantorovich potential which induces the optimal transport map. This involves learning two convex functions, by solving a novel minimax optimization. Building upon recent advances in the field of input convex neural networks, we propose a new framework where the gradient of one convex function represents the optimal transport mapping. Numerical experiments confirm that we learn the optimal transport mapping"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10962","kind":"arxiv","version":2},"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/1908.10962/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":"1908.10962","created_at":"2026-07-05T01:11:09.865013+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10962v2","created_at":"2026-07-05T01:11:09.865013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10962","created_at":"2026-07-05T01:11:09.865013+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXU6T446GI5M","created_at":"2026-07-05T01:11:09.865013+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXU6T446GI5MLODA","created_at":"2026-07-05T01:11:09.865013+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXU6T446","created_at":"2026-07-05T01:11:09.865013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09707","citing_title":"Input convex neural networks as surrogates in mathematical optimisation","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JXU6T446GI5MLODAN7NYR6IETQ","json":"https://pith.science/pith/JXU6T446GI5MLODAN7NYR6IETQ.json","graph_json":"https://pith.science/api/pith-number/JXU6T446GI5MLODAN7NYR6IETQ/graph.json","events_json":"https://pith.science/api/pith-number/JXU6T446GI5MLODAN7NYR6IETQ/events.json","paper":"https://pith.science/paper/JXU6T446"},"agent_actions":{"view_html":"https://pith.science/pith/JXU6T446GI5MLODAN7NYR6IETQ","download_json":"https://pith.science/pith/JXU6T446GI5MLODAN7NYR6IETQ.json","view_paper":"https://pith.science/paper/JXU6T446","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10962&json=true","fetch_graph":"https://pith.science/api/pith-number/JXU6T446GI5MLODAN7NYR6IETQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JXU6T446GI5MLODAN7NYR6IETQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXU6T446GI5MLODAN7NYR6IETQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXU6T446GI5MLODAN7NYR6IETQ/action/storage_attestation","attest_author":"https://pith.science/pith/JXU6T446GI5MLODAN7NYR6IETQ/action/author_attestation","sign_citation":"https://pith.science/pith/JXU6T446GI5MLODAN7NYR6IETQ/action/citation_signature","submit_replication":"https://pith.science/pith/JXU6T446GI5MLODAN7NYR6IETQ/action/replication_record"}},"created_at":"2026-07-05T01:11:09.865013+00:00","updated_at":"2026-07-05T01:11:09.865013+00:00"}