{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3VR26MR46XORBWA5Q3YCBOC7AO","short_pith_number":"pith:3VR26MR4","schema_version":"1.0","canonical_sha256":"dd63af323cf5dd10d81d86f020b85f03adeeb7a24f33a367b5a2baf045acf690","source":{"kind":"arxiv","id":"2102.02992","version":5},"attestation_state":"computed","paper":{"title":"Learning High Dimensional Wasserstein Geodesics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haomin Zhou, Hongyuan Zha, Shaojun Ma, Shu Liu, Yongxin Chen","submitted_at":"2021-02-05T04:25:28Z","abstract_excerpt":"We propose a new formulation and learning strategy for computing the Wasserstein geodesic between two probability distributions in high dimensions. By applying the method of Lagrange multipliers to the dynamic formulation of the optimal transport (OT) problem, we derive a minimax problem whose saddle point is the Wasserstein geodesic. We then parametrize the functions by deep neural networks and design a sample based bidirectional learning algorithm for training. The trained networks enable sampling from the Wasserstein geodesic. As by-products, the algorithm also computes the Wasserstein dist"},"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":"2102.02992","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-05T04:25:28Z","cross_cats_sorted":[],"title_canon_sha256":"c8704fe250e5a897485ab334a3f97eb455309c7a4f80fd82270df3e12ccbe8fa","abstract_canon_sha256":"482dfeab97ac2b928e2f42a86b5f63a6a3d9df49cf936894e0a5621d61218167"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:44.196215Z","signature_b64":"B7F4OAwmwUId5LbFGCj0QhThVbe9WSs4IjgM9NtPlDadpxDFcH0XL2GW+lXEOO06kSnTZzSOvhe5mfmFloVUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd63af323cf5dd10d81d86f020b85f03adeeb7a24f33a367b5a2baf045acf690","last_reissued_at":"2026-07-05T02:46:44.195740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:44.195740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning High Dimensional Wasserstein Geodesics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haomin Zhou, Hongyuan Zha, Shaojun Ma, Shu Liu, Yongxin Chen","submitted_at":"2021-02-05T04:25:28Z","abstract_excerpt":"We propose a new formulation and learning strategy for computing the Wasserstein geodesic between two probability distributions in high dimensions. By applying the method of Lagrange multipliers to the dynamic formulation of the optimal transport (OT) problem, we derive a minimax problem whose saddle point is the Wasserstein geodesic. We then parametrize the functions by deep neural networks and design a sample based bidirectional learning algorithm for training. The trained networks enable sampling from the Wasserstein geodesic. As by-products, the algorithm also computes the Wasserstein dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02992","kind":"arxiv","version":5},"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/2102.02992/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":"2102.02992","created_at":"2026-07-05T02:46:44.195808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.02992v5","created_at":"2026-07-05T02:46:44.195808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02992","created_at":"2026-07-05T02:46:44.195808+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VR26MR46XOR","created_at":"2026-07-05T02:46:44.195808+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VR26MR46XORBWA5","created_at":"2026-07-05T02:46:44.195808+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VR26MR4","created_at":"2026-07-05T02:46:44.195808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10792","citing_title":"Implicit Neural Optimal Transport via Fixed-Point Optimization","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2505.05424","citing_title":"An efficient second-order cone programming approach for dynamic optimal transport on staggered grid discretization","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25182","citing_title":"Learning Monge maps with constrained drifting models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10792","citing_title":"Implicit Neural Optimal Transport via Fixed-Point Optimization","ref_index":243,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VR26MR46XORBWA5Q3YCBOC7AO","json":"https://pith.science/pith/3VR26MR46XORBWA5Q3YCBOC7AO.json","graph_json":"https://pith.science/api/pith-number/3VR26MR46XORBWA5Q3YCBOC7AO/graph.json","events_json":"https://pith.science/api/pith-number/3VR26MR46XORBWA5Q3YCBOC7AO/events.json","paper":"https://pith.science/paper/3VR26MR4"},"agent_actions":{"view_html":"https://pith.science/pith/3VR26MR46XORBWA5Q3YCBOC7AO","download_json":"https://pith.science/pith/3VR26MR46XORBWA5Q3YCBOC7AO.json","view_paper":"https://pith.science/paper/3VR26MR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.02992&json=true","fetch_graph":"https://pith.science/api/pith-number/3VR26MR46XORBWA5Q3YCBOC7AO/graph.json","fetch_events":"https://pith.science/api/pith-number/3VR26MR46XORBWA5Q3YCBOC7AO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VR26MR46XORBWA5Q3YCBOC7AO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VR26MR46XORBWA5Q3YCBOC7AO/action/storage_attestation","attest_author":"https://pith.science/pith/3VR26MR46XORBWA5Q3YCBOC7AO/action/author_attestation","sign_citation":"https://pith.science/pith/3VR26MR46XORBWA5Q3YCBOC7AO/action/citation_signature","submit_replication":"https://pith.science/pith/3VR26MR46XORBWA5Q3YCBOC7AO/action/replication_record"}},"created_at":"2026-07-05T02:46:44.195808+00:00","updated_at":"2026-07-05T02:46:44.195808+00:00"}