{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LCI6Z74LIVCHU4SPYXTFZVUTWW","short_pith_number":"pith:LCI6Z74L","schema_version":"1.0","canonical_sha256":"5891ecff8b45447a724fc5e65cd693b58f652e615503cf6e57f684d1ba1ec8fd","source":{"kind":"arxiv","id":"2404.17442","version":2},"attestation_state":"computed","paper":{"title":"Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin Dupuis, George Deligiannidis, Paul Viallard, Umut Simsekli","submitted_at":"2024-04-26T14:28:18Z","abstract_excerpt":"We propose data-dependent uniform generalization bounds by approaching the problem from a PAC-Bayesian perspective. We first apply the PAC-Bayesian framework on \"random sets\" in a rigorous way, where the training algorithm is assumed to output a data-dependent hypothesis set after observing the training data. This approach allows us to prove data-dependent bounds, which can be applicable in numerous contexts. To highlight the power of our approach, we consider two main applications. First, we propose a PAC-Bayesian formulation of the recently developed fractal-dimension-based generalization bo"},"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":"2404.17442","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-04-26T14:28:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"06bd17e55f647564ac68148ca49ff22b9c7aca529810c9cf37a3f7d604aeede5","abstract_canon_sha256":"83189fc337746f345d3412e8f47d5d97ccafdff087dd397c35360d3e5fe79263"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:58.511780Z","signature_b64":"AhKh3nkPBXckAaVqpjSkKSP/oJK2lr5Eo+Y2dzbVOSaom7Bgxes+ijbBzs1d5qTJMDQahXBf6eqlLHWMWQ+IAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5891ecff8b45447a724fc5e65cd693b58f652e615503cf6e57f684d1ba1ec8fd","last_reissued_at":"2026-07-05T10:11:58.511291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:58.511291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin Dupuis, George Deligiannidis, Paul Viallard, Umut Simsekli","submitted_at":"2024-04-26T14:28:18Z","abstract_excerpt":"We propose data-dependent uniform generalization bounds by approaching the problem from a PAC-Bayesian perspective. We first apply the PAC-Bayesian framework on \"random sets\" in a rigorous way, where the training algorithm is assumed to output a data-dependent hypothesis set after observing the training data. This approach allows us to prove data-dependent bounds, which can be applicable in numerous contexts. To highlight the power of our approach, we consider two main applications. First, we propose a PAC-Bayesian formulation of the recently developed fractal-dimension-based generalization bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17442","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/2404.17442/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":"2404.17442","created_at":"2026-07-05T10:11:58.511367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17442v2","created_at":"2026-07-05T10:11:58.511367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17442","created_at":"2026-07-05T10:11:58.511367+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCI6Z74LIVCH","created_at":"2026-07-05T10:11:58.511367+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCI6Z74LIVCHU4SP","created_at":"2026-07-05T10:11:58.511367+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCI6Z74L","created_at":"2026-07-05T10:11:58.511367+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.04950","citing_title":"Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCI6Z74LIVCHU4SPYXTFZVUTWW","json":"https://pith.science/pith/LCI6Z74LIVCHU4SPYXTFZVUTWW.json","graph_json":"https://pith.science/api/pith-number/LCI6Z74LIVCHU4SPYXTFZVUTWW/graph.json","events_json":"https://pith.science/api/pith-number/LCI6Z74LIVCHU4SPYXTFZVUTWW/events.json","paper":"https://pith.science/paper/LCI6Z74L"},"agent_actions":{"view_html":"https://pith.science/pith/LCI6Z74LIVCHU4SPYXTFZVUTWW","download_json":"https://pith.science/pith/LCI6Z74LIVCHU4SPYXTFZVUTWW.json","view_paper":"https://pith.science/paper/LCI6Z74L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17442&json=true","fetch_graph":"https://pith.science/api/pith-number/LCI6Z74LIVCHU4SPYXTFZVUTWW/graph.json","fetch_events":"https://pith.science/api/pith-number/LCI6Z74LIVCHU4SPYXTFZVUTWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCI6Z74LIVCHU4SPYXTFZVUTWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCI6Z74LIVCHU4SPYXTFZVUTWW/action/storage_attestation","attest_author":"https://pith.science/pith/LCI6Z74LIVCHU4SPYXTFZVUTWW/action/author_attestation","sign_citation":"https://pith.science/pith/LCI6Z74LIVCHU4SPYXTFZVUTWW/action/citation_signature","submit_replication":"https://pith.science/pith/LCI6Z74LIVCHU4SPYXTFZVUTWW/action/replication_record"}},"created_at":"2026-07-05T10:11:58.511367+00:00","updated_at":"2026-07-05T10:11:58.511367+00:00"}