{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:POUCFTYMNOLLAVBHVKWS7XW7WC","short_pith_number":"pith:POUCFTYM","schema_version":"1.0","canonical_sha256":"7ba822cf0c6b96b05427aaad2fdedfb088d9782819625bc8341bb73ad168db08","source":{"kind":"arxiv","id":"2502.14544","version":1},"attestation_state":"computed","paper":{"title":"Generalization Error of $f$-Divergence Stabilized Algorithms via Duality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Francisco Daunas, Gholamali Aminian, I\\~naki Esnaola, Samir M. Perlaza","submitted_at":"2025-02-20T13:21:01Z","abstract_excerpt":"The solution to empirical risk minimization with $f$-divergence regularization (ERM-$f$DR) is extended to constrained optimization problems, establishing conditions for equivalence between the solution and constraints. A dual formulation of ERM-$f$DR is introduced, providing a computationally efficient method to derive the normalization function of the ERM-$f$DR solution. This dual approach leverages the Legendre-Fenchel transform and the implicit function theorem, enabling explicit characterizations of the generalization error for general algorithms under mild conditions, and another for ERM-"},"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":"2502.14544","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-20T13:21:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5cac05d4db7931f42de134d9f5df94c8ec2e942a8a508326540c9a388dc831e9","abstract_canon_sha256":"d489d9e4368896c044867bb0b905ef7e1d3b9258c351703f00359bdb46a13b61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:28.836409Z","signature_b64":"E+ydSTZB55UP3woxjBtFz1Pyisxaes4F8dv/ziIWK3i6dBsobPgIJN+9AEvkV2u4UAAonhiBDG99osFN2UseDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ba822cf0c6b96b05427aaad2fdedfb088d9782819625bc8341bb73ad168db08","last_reissued_at":"2026-07-05T10:17:28.835752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:28.835752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization Error of $f$-Divergence Stabilized Algorithms via Duality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Francisco Daunas, Gholamali Aminian, I\\~naki Esnaola, Samir M. Perlaza","submitted_at":"2025-02-20T13:21:01Z","abstract_excerpt":"The solution to empirical risk minimization with $f$-divergence regularization (ERM-$f$DR) is extended to constrained optimization problems, establishing conditions for equivalence between the solution and constraints. A dual formulation of ERM-$f$DR is introduced, providing a computationally efficient method to derive the normalization function of the ERM-$f$DR solution. This dual approach leverages the Legendre-Fenchel transform and the implicit function theorem, enabling explicit characterizations of the generalization error for general algorithms under mild conditions, and another for ERM-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14544","kind":"arxiv","version":1},"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/2502.14544/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":"2502.14544","created_at":"2026-07-05T10:17:28.835857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14544v1","created_at":"2026-07-05T10:17:28.835857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14544","created_at":"2026-07-05T10:17:28.835857+00:00"},{"alias_kind":"pith_short_12","alias_value":"POUCFTYMNOLL","created_at":"2026-07-05T10:17:28.835857+00:00"},{"alias_kind":"pith_short_16","alias_value":"POUCFTYMNOLLAVBH","created_at":"2026-07-05T10:17:28.835857+00:00"},{"alias_kind":"pith_short_8","alias_value":"POUCFTYM","created_at":"2026-07-05T10:17:28.835857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03109","citing_title":"On Weak-to-Strong Generalization and f-Divergence","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POUCFTYMNOLLAVBHVKWS7XW7WC","json":"https://pith.science/pith/POUCFTYMNOLLAVBHVKWS7XW7WC.json","graph_json":"https://pith.science/api/pith-number/POUCFTYMNOLLAVBHVKWS7XW7WC/graph.json","events_json":"https://pith.science/api/pith-number/POUCFTYMNOLLAVBHVKWS7XW7WC/events.json","paper":"https://pith.science/paper/POUCFTYM"},"agent_actions":{"view_html":"https://pith.science/pith/POUCFTYMNOLLAVBHVKWS7XW7WC","download_json":"https://pith.science/pith/POUCFTYMNOLLAVBHVKWS7XW7WC.json","view_paper":"https://pith.science/paper/POUCFTYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14544&json=true","fetch_graph":"https://pith.science/api/pith-number/POUCFTYMNOLLAVBHVKWS7XW7WC/graph.json","fetch_events":"https://pith.science/api/pith-number/POUCFTYMNOLLAVBHVKWS7XW7WC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POUCFTYMNOLLAVBHVKWS7XW7WC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POUCFTYMNOLLAVBHVKWS7XW7WC/action/storage_attestation","attest_author":"https://pith.science/pith/POUCFTYMNOLLAVBHVKWS7XW7WC/action/author_attestation","sign_citation":"https://pith.science/pith/POUCFTYMNOLLAVBHVKWS7XW7WC/action/citation_signature","submit_replication":"https://pith.science/pith/POUCFTYMNOLLAVBHVKWS7XW7WC/action/replication_record"}},"created_at":"2026-07-05T10:17:28.835857+00:00","updated_at":"2026-07-05T10:17:28.835857+00:00"}