{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NJYOZFR2COA7JMVNUIWQITOM3F","short_pith_number":"pith:NJYOZFR2","schema_version":"1.0","canonical_sha256":"6a70ec963a1381f4b2ada22d044dccd97ec6b5135f2e73f50a48da747b2d205f","source":{"kind":"arxiv","id":"2007.04462","version":3},"attestation_state":"computed","paper":{"title":"Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amirhossein Taghvaei, Jiaojiao Fan, Yongxin Chen","submitted_at":"2020-07-08T22:41:18Z","abstract_excerpt":"Wasserstein Barycenter is a principled approach to represent the weighted mean of a given set of probability distributions, utilizing the geometry induced by optimal transport. In this work, we present a novel scalable algorithm to approximate the Wasserstein Barycenters aiming at high-dimensional applications in machine learning. Our proposed algorithm is based on the Kantorovich dual formulation of the Wasserstein-2 distance as well as a recent neural network architecture, input convex neural network, that is known to parametrize convex functions. The distinguishing features of our method ar"},"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":"2007.04462","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T22:41:18Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"4367a857adc4223560b2d45213245eb74885441fa2bc8d11307e4d7f036e6325","abstract_canon_sha256":"cd07832015726bac523858227857f357af610782ff693d5d1d9062b2d7b451f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:25.929614Z","signature_b64":"NtF46Ga033EKpoujDdOX4WL+XiOTF2EO2q3Da7HZ3CId08Y20l/gEp4p0fPvQH69Zm5Mgm/M23eJCHgF1up2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a70ec963a1381f4b2ada22d044dccd97ec6b5135f2e73f50a48da747b2d205f","last_reissued_at":"2026-07-05T03:35:25.929177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:25.929177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amirhossein Taghvaei, Jiaojiao Fan, Yongxin Chen","submitted_at":"2020-07-08T22:41:18Z","abstract_excerpt":"Wasserstein Barycenter is a principled approach to represent the weighted mean of a given set of probability distributions, utilizing the geometry induced by optimal transport. In this work, we present a novel scalable algorithm to approximate the Wasserstein Barycenters aiming at high-dimensional applications in machine learning. Our proposed algorithm is based on the Kantorovich dual formulation of the Wasserstein-2 distance as well as a recent neural network architecture, input convex neural network, that is known to parametrize convex functions. The distinguishing features of our method ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04462","kind":"arxiv","version":3},"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/2007.04462/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":"2007.04462","created_at":"2026-07-05T03:35:25.929232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.04462v3","created_at":"2026-07-05T03:35:25.929232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04462","created_at":"2026-07-05T03:35:25.929232+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJYOZFR2COA7","created_at":"2026-07-05T03:35:25.929232+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJYOZFR2COA7JMVN","created_at":"2026-07-05T03:35:25.929232+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJYOZFR2","created_at":"2026-07-05T03:35:25.929232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NJYOZFR2COA7JMVNUIWQITOM3F","json":"https://pith.science/pith/NJYOZFR2COA7JMVNUIWQITOM3F.json","graph_json":"https://pith.science/api/pith-number/NJYOZFR2COA7JMVNUIWQITOM3F/graph.json","events_json":"https://pith.science/api/pith-number/NJYOZFR2COA7JMVNUIWQITOM3F/events.json","paper":"https://pith.science/paper/NJYOZFR2"},"agent_actions":{"view_html":"https://pith.science/pith/NJYOZFR2COA7JMVNUIWQITOM3F","download_json":"https://pith.science/pith/NJYOZFR2COA7JMVNUIWQITOM3F.json","view_paper":"https://pith.science/paper/NJYOZFR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.04462&json=true","fetch_graph":"https://pith.science/api/pith-number/NJYOZFR2COA7JMVNUIWQITOM3F/graph.json","fetch_events":"https://pith.science/api/pith-number/NJYOZFR2COA7JMVNUIWQITOM3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJYOZFR2COA7JMVNUIWQITOM3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJYOZFR2COA7JMVNUIWQITOM3F/action/storage_attestation","attest_author":"https://pith.science/pith/NJYOZFR2COA7JMVNUIWQITOM3F/action/author_attestation","sign_citation":"https://pith.science/pith/NJYOZFR2COA7JMVNUIWQITOM3F/action/citation_signature","submit_replication":"https://pith.science/pith/NJYOZFR2COA7JMVNUIWQITOM3F/action/replication_record"}},"created_at":"2026-07-05T03:35:25.929232+00:00","updated_at":"2026-07-05T03:35:25.929232+00:00"}