{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WTBEHZA4L2QDBX5STQPZTJWT5S","short_pith_number":"pith:WTBEHZA4","schema_version":"1.0","canonical_sha256":"b4c243e41c5ea030dfb29c1f99a6d3ec9cbf5d39dca6cdbb0c80c32ea04f5a3c","source":{"kind":"arxiv","id":"2505.02621","version":2},"attestation_state":"computed","paper":{"title":"Mirror Mean-Field Langevin Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anming Gu, Juno Kim","submitted_at":"2025-05-05T12:49:42Z","abstract_excerpt":"The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional on the Wasserstein space over $\\mathbb{R}^d$, and has gained attention recently as a model for the gradient descent dynamics of interacting particle systems such as infinite-width two-layer neural networks. However, many problems of interest have constrained domains, which are not solved by existing mean-field algorithms due to the global diffusion term. We study the optimization of probability measures constrained to a convex subset of $\\mathbb{R}^d$ by proposing the \\emph{mirror mean-field La"},"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":"2505.02621","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T12:49:42Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"e8ae3ae90de1f53356470cd4286f63ab2a120424793e52a9d0e43604fc5fac5b","abstract_canon_sha256":"0ab36073b37b4a922be0b12a21f905672f8e573da27b4005a1f3c25c41859a15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:08.995632Z","signature_b64":"vM+ZWjiWK8iZZ2xTLEKjMTkoh0Xp3/Jbz4hAqra7gr1C9oLIjf1Zbs5wPYCnhSNQJTIagVk3ogTexUQh1SobDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4c243e41c5ea030dfb29c1f99a6d3ec9cbf5d39dca6cdbb0c80c32ea04f5a3c","last_reissued_at":"2026-05-20T00:04:08.994816Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:08.994816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mirror Mean-Field Langevin Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anming Gu, Juno Kim","submitted_at":"2025-05-05T12:49:42Z","abstract_excerpt":"The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional on the Wasserstein space over $\\mathbb{R}^d$, and has gained attention recently as a model for the gradient descent dynamics of interacting particle systems such as infinite-width two-layer neural networks. However, many problems of interest have constrained domains, which are not solved by existing mean-field algorithms due to the global diffusion term. We study the optimization of probability measures constrained to a convex subset of $\\mathbb{R}^d$ by proposing the \\emph{mirror mean-field La"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02621","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/2505.02621/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":"2505.02621","created_at":"2026-05-20T00:04:08.994955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02621v2","created_at":"2026-05-20T00:04:08.994955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02621","created_at":"2026-05-20T00:04:08.994955+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTBEHZA4L2QD","created_at":"2026-05-20T00:04:08.994955+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTBEHZA4L2QDBX5S","created_at":"2026-05-20T00:04:08.994955+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTBEHZA4","created_at":"2026-05-20T00:04:08.994955+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/WTBEHZA4L2QDBX5STQPZTJWT5S","json":"https://pith.science/pith/WTBEHZA4L2QDBX5STQPZTJWT5S.json","graph_json":"https://pith.science/api/pith-number/WTBEHZA4L2QDBX5STQPZTJWT5S/graph.json","events_json":"https://pith.science/api/pith-number/WTBEHZA4L2QDBX5STQPZTJWT5S/events.json","paper":"https://pith.science/paper/WTBEHZA4"},"agent_actions":{"view_html":"https://pith.science/pith/WTBEHZA4L2QDBX5STQPZTJWT5S","download_json":"https://pith.science/pith/WTBEHZA4L2QDBX5STQPZTJWT5S.json","view_paper":"https://pith.science/paper/WTBEHZA4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02621&json=true","fetch_graph":"https://pith.science/api/pith-number/WTBEHZA4L2QDBX5STQPZTJWT5S/graph.json","fetch_events":"https://pith.science/api/pith-number/WTBEHZA4L2QDBX5STQPZTJWT5S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTBEHZA4L2QDBX5STQPZTJWT5S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTBEHZA4L2QDBX5STQPZTJWT5S/action/storage_attestation","attest_author":"https://pith.science/pith/WTBEHZA4L2QDBX5STQPZTJWT5S/action/author_attestation","sign_citation":"https://pith.science/pith/WTBEHZA4L2QDBX5STQPZTJWT5S/action/citation_signature","submit_replication":"https://pith.science/pith/WTBEHZA4L2QDBX5STQPZTJWT5S/action/replication_record"}},"created_at":"2026-05-20T00:04:08.994955+00:00","updated_at":"2026-05-20T00:04:08.994955+00:00"}