{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KCSB3MZGXBJMPET4U3Q4KW3GW3","short_pith_number":"pith:KCSB3MZG","schema_version":"1.0","canonical_sha256":"50a41db326b852c7927ca6e1c55b66b6f7b67709fa7b3f2e08c3c1eb10cea417","source":{"kind":"arxiv","id":"1711.02283","version":2},"attestation_state":"computed","paper":{"title":"Large-Scale Optimal Transport and Mapping Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Antoine Rolet, Bharath Bhushan Damodaran, Mathieu Blondel, Nicolas Courty, R\\'emi Flamary, Vivien Seguy","submitted_at":"2017-11-07T04:53:07Z","abstract_excerpt":"This paper presents a novel two-step approach for the fundamental problem of learning an optimal map from one distribution to another. First, we learn an optimal transport (OT) plan, which can be thought as a one-to-many map between the two distributions. To that end, we propose a stochastic dual approach of regularized OT, and show empirically that it scales better than a recent related approach when the amount of samples is very large. Second, we estimate a \\textit{Monge map} as a deep neural network learned by approximating the barycentric projection of the previously-obtained OT plan. This"},"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":"1711.02283","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-07T04:53:07Z","cross_cats_sorted":[],"title_canon_sha256":"cc65ed4fb724cf0a32b15c87c9f5c01326c2953b2f7ed9e32db2c0a93d6ce5bc","abstract_canon_sha256":"5ce8aed24fe8bce3d528030456dd88421ef21b83257778ac09f52ddd09b35304"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:39.247157Z","signature_b64":"onW1yn2sNR0NBQmISRFEFpOTINBvxWDykLul/dgSd8omZs1V8m+cXJxuGdTdrkjTLbsU7oYiHPclQXPDE03QDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50a41db326b852c7927ca6e1c55b66b6f7b67709fa7b3f2e08c3c1eb10cea417","last_reissued_at":"2026-05-18T00:22:39.246809Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:39.246809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Optimal Transport and Mapping Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Antoine Rolet, Bharath Bhushan Damodaran, Mathieu Blondel, Nicolas Courty, R\\'emi Flamary, Vivien Seguy","submitted_at":"2017-11-07T04:53:07Z","abstract_excerpt":"This paper presents a novel two-step approach for the fundamental problem of learning an optimal map from one distribution to another. First, we learn an optimal transport (OT) plan, which can be thought as a one-to-many map between the two distributions. To that end, we propose a stochastic dual approach of regularized OT, and show empirically that it scales better than a recent related approach when the amount of samples is very large. Second, we estimate a \\textit{Monge map} as a deep neural network learned by approximating the barycentric projection of the previously-obtained OT plan. This"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.02283","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":""},"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":"1711.02283","created_at":"2026-05-18T00:22:39.246866+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.02283v2","created_at":"2026-05-18T00:22:39.246866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.02283","created_at":"2026-05-18T00:22:39.246866+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCSB3MZGXBJM","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCSB3MZGXBJMPET4","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCSB3MZG","created_at":"2026-05-18T12:31:24.725408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09691","citing_title":"Adversarial Computation of Optimal Transport Maps","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26942","citing_title":"Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10792","citing_title":"Fixed-Point Neural Optimal Transport without Implicit Differentiation","ref_index":257,"is_internal_anchor":false},{"citing_arxiv_id":"2209.03003","citing_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCSB3MZGXBJMPET4U3Q4KW3GW3","json":"https://pith.science/pith/KCSB3MZGXBJMPET4U3Q4KW3GW3.json","graph_json":"https://pith.science/api/pith-number/KCSB3MZGXBJMPET4U3Q4KW3GW3/graph.json","events_json":"https://pith.science/api/pith-number/KCSB3MZGXBJMPET4U3Q4KW3GW3/events.json","paper":"https://pith.science/paper/KCSB3MZG"},"agent_actions":{"view_html":"https://pith.science/pith/KCSB3MZGXBJMPET4U3Q4KW3GW3","download_json":"https://pith.science/pith/KCSB3MZGXBJMPET4U3Q4KW3GW3.json","view_paper":"https://pith.science/paper/KCSB3MZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.02283&json=true","fetch_graph":"https://pith.science/api/pith-number/KCSB3MZGXBJMPET4U3Q4KW3GW3/graph.json","fetch_events":"https://pith.science/api/pith-number/KCSB3MZGXBJMPET4U3Q4KW3GW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCSB3MZGXBJMPET4U3Q4KW3GW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCSB3MZGXBJMPET4U3Q4KW3GW3/action/storage_attestation","attest_author":"https://pith.science/pith/KCSB3MZGXBJMPET4U3Q4KW3GW3/action/author_attestation","sign_citation":"https://pith.science/pith/KCSB3MZGXBJMPET4U3Q4KW3GW3/action/citation_signature","submit_replication":"https://pith.science/pith/KCSB3MZGXBJMPET4U3Q4KW3GW3/action/replication_record"}},"created_at":"2026-05-18T00:22:39.246866+00:00","updated_at":"2026-05-18T00:22:39.246866+00:00"}