{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UAGED5W3T3TCG2YKMHZXRVR6A5","short_pith_number":"pith:UAGED5W3","schema_version":"1.0","canonical_sha256":"a00c41f6db9ee6236b0a61f378d63e077d927a351ceb2c7f7ee4a55676d95360","source":{"kind":"arxiv","id":"2402.04613","version":4},"attestation_state":"computed","paper":{"title":"Wasserstein Gradient Flows for Moreau Envelopes of f-Divergences in Reproducing Kernel Hilbert Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.FA","math.OC"],"primary_cat":"stat.ML","authors_text":"Gabriele Steidl, Nicolaj Rux, Sebastian Neumayer, Viktor Stein","submitted_at":"2024-02-07T06:30:39Z","abstract_excerpt":"Commonly used $f$-divergences of measures, e.g., the Kullback-Leibler divergence, are subject to limitations regarding the support of the involved measures. A remedy is regularizing the $f$-divergence by a squared maximum mean discrepancy (MMD) associated with a characteristic kernel $K$. We use the kernel mean embedding to show that this regularization can be rewritten as the Moreau envelope of some function on the associated reproducing kernel Hilbert space. Then, we exploit well-known results on Moreau envelopes in Hilbert spaces to analyze the MMD-regularized $f$-divergences, particularly "},"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":"2402.04613","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-07T06:30:39Z","cross_cats_sorted":["cs.LG","math.FA","math.OC"],"title_canon_sha256":"043f7f805ef514b33d101201d4ceba1f00c3253f92eb11d0ee17ea270b6fc854","abstract_canon_sha256":"24d4137ed6375acfce4415ebe789edde2d384dcb1b4e8f6f0b5c888228c79728"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:24.975929Z","signature_b64":"FAhFR0QjvHEy6+NsPkD/2YxrKlSTZBnRFlisS5ydp7Qbta8PoRh2oWLG5RfZWFaWonHmayziiw6EcXij+cFZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a00c41f6db9ee6236b0a61f378d63e077d927a351ceb2c7f7ee4a55676d95360","last_reissued_at":"2026-07-05T10:47:24.975413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:24.975413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wasserstein Gradient Flows for Moreau Envelopes of f-Divergences in Reproducing Kernel Hilbert Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.FA","math.OC"],"primary_cat":"stat.ML","authors_text":"Gabriele Steidl, Nicolaj Rux, Sebastian Neumayer, Viktor Stein","submitted_at":"2024-02-07T06:30:39Z","abstract_excerpt":"Commonly used $f$-divergences of measures, e.g., the Kullback-Leibler divergence, are subject to limitations regarding the support of the involved measures. A remedy is regularizing the $f$-divergence by a squared maximum mean discrepancy (MMD) associated with a characteristic kernel $K$. We use the kernel mean embedding to show that this regularization can be rewritten as the Moreau envelope of some function on the associated reproducing kernel Hilbert space. Then, we exploit well-known results on Moreau envelopes in Hilbert spaces to analyze the MMD-regularized $f$-divergences, particularly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04613","kind":"arxiv","version":4},"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/2402.04613/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":"2402.04613","created_at":"2026-07-05T10:47:24.975494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04613v4","created_at":"2026-07-05T10:47:24.975494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04613","created_at":"2026-07-05T10:47:24.975494+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAGED5W3T3TC","created_at":"2026-07-05T10:47:24.975494+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAGED5W3T3TCG2YK","created_at":"2026-07-05T10:47:24.975494+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAGED5W3","created_at":"2026-07-05T10:47:24.975494+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.10600","citing_title":"Weighted quantization using MMD: From mean field to mean shift via gradient flows","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UAGED5W3T3TCG2YKMHZXRVR6A5","json":"https://pith.science/pith/UAGED5W3T3TCG2YKMHZXRVR6A5.json","graph_json":"https://pith.science/api/pith-number/UAGED5W3T3TCG2YKMHZXRVR6A5/graph.json","events_json":"https://pith.science/api/pith-number/UAGED5W3T3TCG2YKMHZXRVR6A5/events.json","paper":"https://pith.science/paper/UAGED5W3"},"agent_actions":{"view_html":"https://pith.science/pith/UAGED5W3T3TCG2YKMHZXRVR6A5","download_json":"https://pith.science/pith/UAGED5W3T3TCG2YKMHZXRVR6A5.json","view_paper":"https://pith.science/paper/UAGED5W3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04613&json=true","fetch_graph":"https://pith.science/api/pith-number/UAGED5W3T3TCG2YKMHZXRVR6A5/graph.json","fetch_events":"https://pith.science/api/pith-number/UAGED5W3T3TCG2YKMHZXRVR6A5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAGED5W3T3TCG2YKMHZXRVR6A5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAGED5W3T3TCG2YKMHZXRVR6A5/action/storage_attestation","attest_author":"https://pith.science/pith/UAGED5W3T3TCG2YKMHZXRVR6A5/action/author_attestation","sign_citation":"https://pith.science/pith/UAGED5W3T3TCG2YKMHZXRVR6A5/action/citation_signature","submit_replication":"https://pith.science/pith/UAGED5W3T3TCG2YKMHZXRVR6A5/action/replication_record"}},"created_at":"2026-07-05T10:47:24.975494+00:00","updated_at":"2026-07-05T10:47:24.975494+00:00"}