{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YYGCSB4PCWVC77BXW7JS7FQAYV","short_pith_number":"pith:YYGCSB4P","schema_version":"1.0","canonical_sha256":"c60c29078f15aa2ffc37b7d32f9600c5421dcd5d1aca93c152cc95f086d0ae3e","source":{"kind":"arxiv","id":"2409.19431","version":3},"attestation_state":"computed","paper":{"title":"Generalization and Robustness of the Tilted Empirical Risk","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Ahmad Beirami, Amir R. Asadi, Gesine Reinert, Gholamali Aminian, Samuel N. Cohen, Tian Li","submitted_at":"2024-09-28T18:31:51Z","abstract_excerpt":"The generalization error (risk) of a supervised statistical learning algorithm quantifies its prediction ability on previously unseen data. Inspired by exponential tilting, \\citet{li2020tilted} proposed the {\\it tilted empirical risk} (TER) as a non-linear risk metric for machine learning applications such as classification and regression problems. In this work, we examine the generalization error of the tilted empirical risk in the robustness regime under \\textit{negative tilt}. Our first contribution is to provide uniform and information-theoretic bounds on the {\\it tilted generalization err"},"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":"2409.19431","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-09-28T18:31:51Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"404fa53ebf5b2d6e510586e7a3af1aeeaacd4d198c051a5ad77375345f88546b","abstract_canon_sha256":"8a351adbc7510021e8e7b836f5d0440ce658e5513a76b1bac97884b785598239"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:35.945325Z","signature_b64":"DjmtwpTiw4eeRKmBFg6K4ao3gInmsRE12fLc7rZsjPOpY/26M9kNmzTE9GVA7/y0wxh1CJS9iRNmuGRO2hskDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c60c29078f15aa2ffc37b7d32f9600c5421dcd5d1aca93c152cc95f086d0ae3e","last_reissued_at":"2026-07-05T11:17:35.944840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:35.944840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization and Robustness of the Tilted Empirical Risk","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Ahmad Beirami, Amir R. Asadi, Gesine Reinert, Gholamali Aminian, Samuel N. Cohen, Tian Li","submitted_at":"2024-09-28T18:31:51Z","abstract_excerpt":"The generalization error (risk) of a supervised statistical learning algorithm quantifies its prediction ability on previously unseen data. Inspired by exponential tilting, \\citet{li2020tilted} proposed the {\\it tilted empirical risk} (TER) as a non-linear risk metric for machine learning applications such as classification and regression problems. In this work, we examine the generalization error of the tilted empirical risk in the robustness regime under \\textit{negative tilt}. Our first contribution is to provide uniform and information-theoretic bounds on the {\\it tilted generalization err"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19431","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/2409.19431/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":"2409.19431","created_at":"2026-07-05T11:17:35.944898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19431v3","created_at":"2026-07-05T11:17:35.944898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19431","created_at":"2026-07-05T11:17:35.944898+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYGCSB4PCWVC","created_at":"2026-07-05T11:17:35.944898+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYGCSB4PCWVC77BX","created_at":"2026-07-05T11:17:35.944898+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYGCSB4P","created_at":"2026-07-05T11:17:35.944898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21369","citing_title":"Quantum Learning with Tunable Loss Functions","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYGCSB4PCWVC77BXW7JS7FQAYV","json":"https://pith.science/pith/YYGCSB4PCWVC77BXW7JS7FQAYV.json","graph_json":"https://pith.science/api/pith-number/YYGCSB4PCWVC77BXW7JS7FQAYV/graph.json","events_json":"https://pith.science/api/pith-number/YYGCSB4PCWVC77BXW7JS7FQAYV/events.json","paper":"https://pith.science/paper/YYGCSB4P"},"agent_actions":{"view_html":"https://pith.science/pith/YYGCSB4PCWVC77BXW7JS7FQAYV","download_json":"https://pith.science/pith/YYGCSB4PCWVC77BXW7JS7FQAYV.json","view_paper":"https://pith.science/paper/YYGCSB4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19431&json=true","fetch_graph":"https://pith.science/api/pith-number/YYGCSB4PCWVC77BXW7JS7FQAYV/graph.json","fetch_events":"https://pith.science/api/pith-number/YYGCSB4PCWVC77BXW7JS7FQAYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYGCSB4PCWVC77BXW7JS7FQAYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYGCSB4PCWVC77BXW7JS7FQAYV/action/storage_attestation","attest_author":"https://pith.science/pith/YYGCSB4PCWVC77BXW7JS7FQAYV/action/author_attestation","sign_citation":"https://pith.science/pith/YYGCSB4PCWVC77BXW7JS7FQAYV/action/citation_signature","submit_replication":"https://pith.science/pith/YYGCSB4PCWVC77BXW7JS7FQAYV/action/replication_record"}},"created_at":"2026-07-05T11:17:35.944898+00:00","updated_at":"2026-07-05T11:17:35.944898+00:00"}