{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I74WVEBSX7ZKMZKSWOA2XUZSEI","short_pith_number":"pith:I74WVEBS","schema_version":"1.0","canonical_sha256":"47f96a9032bff2a66552b381abd3322216b993731320cdcb1f7023f61446f16f","source":{"kind":"arxiv","id":"2501.14993","version":3},"attestation_state":"computed","paper":{"title":"Convergence Analysis of the Wasserstein Proximal Algorithm beyond Geodesic Convexity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Shuailong Zhu, Xiaohui Chen","submitted_at":"2025-01-25T00:00:50Z","abstract_excerpt":"The proximal algorithm is a powerful tool to minimize nonlinear and nonsmooth functionals in a general metric space. Motivated by the recent progress in studying the training dynamics of the noisy gradient descent algorithm on two-layer neural networks in the mean-field regime, we provide in this paper a simple and self-contained analysis for the convergence of the general-purpose Wasserstein proximal algorithm without assuming geodesic convexity of the objective functional. Under a natural Wasserstein analog of the Euclidean Polyak-{\\L}ojasiewicz inequality, we establish that the proximal alg"},"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":"2501.14993","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2025-01-25T00:00:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a2ec6c5ea9830f97e125bf1ee94a8784f4abf068bcc6506061b3202cd67ea140","abstract_canon_sha256":"3cb3befa31ee9028f39868319683ff007871a88245d8d392d7e08d78c467e2b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:26.841333Z","signature_b64":"UzWlbbGm4xo1OxtSLMoP3wnrPjLwO+d0HbvcMQDLUVK01/Q949CQTjWiHDNtPutSi23kKlkmafFV9uEyq0ZqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47f96a9032bff2a66552b381abd3322216b993731320cdcb1f7023f61446f16f","last_reissued_at":"2026-05-20T00:05:26.840494Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:26.840494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence Analysis of the Wasserstein Proximal Algorithm beyond Geodesic Convexity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Shuailong Zhu, Xiaohui Chen","submitted_at":"2025-01-25T00:00:50Z","abstract_excerpt":"The proximal algorithm is a powerful tool to minimize nonlinear and nonsmooth functionals in a general metric space. Motivated by the recent progress in studying the training dynamics of the noisy gradient descent algorithm on two-layer neural networks in the mean-field regime, we provide in this paper a simple and self-contained analysis for the convergence of the general-purpose Wasserstein proximal algorithm without assuming geodesic convexity of the objective functional. Under a natural Wasserstein analog of the Euclidean Polyak-{\\L}ojasiewicz inequality, we establish that the proximal alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14993","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/2501.14993/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":"2501.14993","created_at":"2026-05-20T00:05:26.840647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14993v3","created_at":"2026-05-20T00:05:26.840647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14993","created_at":"2026-05-20T00:05:26.840647+00:00"},{"alias_kind":"pith_short_12","alias_value":"I74WVEBSX7ZK","created_at":"2026-05-20T00:05:26.840647+00:00"},{"alias_kind":"pith_short_16","alias_value":"I74WVEBSX7ZKMZKS","created_at":"2026-05-20T00:05:26.840647+00:00"},{"alias_kind":"pith_short_8","alias_value":"I74WVEBS","created_at":"2026-05-20T00:05:26.840647+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17963","citing_title":"From Saddle Points Toward Global Minima: A Newton-Type Method on Wasserstein Space","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I74WVEBSX7ZKMZKSWOA2XUZSEI","json":"https://pith.science/pith/I74WVEBSX7ZKMZKSWOA2XUZSEI.json","graph_json":"https://pith.science/api/pith-number/I74WVEBSX7ZKMZKSWOA2XUZSEI/graph.json","events_json":"https://pith.science/api/pith-number/I74WVEBSX7ZKMZKSWOA2XUZSEI/events.json","paper":"https://pith.science/paper/I74WVEBS"},"agent_actions":{"view_html":"https://pith.science/pith/I74WVEBSX7ZKMZKSWOA2XUZSEI","download_json":"https://pith.science/pith/I74WVEBSX7ZKMZKSWOA2XUZSEI.json","view_paper":"https://pith.science/paper/I74WVEBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14993&json=true","fetch_graph":"https://pith.science/api/pith-number/I74WVEBSX7ZKMZKSWOA2XUZSEI/graph.json","fetch_events":"https://pith.science/api/pith-number/I74WVEBSX7ZKMZKSWOA2XUZSEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I74WVEBSX7ZKMZKSWOA2XUZSEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I74WVEBSX7ZKMZKSWOA2XUZSEI/action/storage_attestation","attest_author":"https://pith.science/pith/I74WVEBSX7ZKMZKSWOA2XUZSEI/action/author_attestation","sign_citation":"https://pith.science/pith/I74WVEBSX7ZKMZKSWOA2XUZSEI/action/citation_signature","submit_replication":"https://pith.science/pith/I74WVEBSX7ZKMZKSWOA2XUZSEI/action/replication_record"}},"created_at":"2026-05-20T00:05:26.840647+00:00","updated_at":"2026-05-20T00:05:26.840647+00:00"}