{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UHEXEBHSLIBMKROR5LKUQJ3DR4","short_pith_number":"pith:UHEXEBHS","schema_version":"1.0","canonical_sha256":"a1c97204f25a02c545d1ead54827638f005e902107e6243a8b57f352eb6e1289","source":{"kind":"arxiv","id":"2106.03542","version":4},"attestation_state":"computed","paper":{"title":"How Tight Can PAC-Bayes be in the Small Data Regime?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Andrew Y. K. Foong, David R. Burt, Richard E. Turner, Wessel P. Bruinsma","submitted_at":"2021-06-07T12:11:32Z","abstract_excerpt":"In this paper, we investigate the question: Given a small number of datapoints, for example N = 30, how tight can PAC-Bayes and test set bounds be made? For such small datasets, test set bounds adversely affect generalisation performance by withholding data from the training procedure. In this setting, PAC-Bayes bounds are especially attractive, due to their ability to use all the data to simultaneously learn a posterior and bound its generalisation risk. We focus on the case of i.i.d. data with a bounded loss and consider the generic PAC-Bayes theorem of Germain et al. While their theorem is "},"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":"2106.03542","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-07T12:11:32Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"d96d94aaa4e369157bc2cdead8a2c6d67a1bdba092161d9fa9060ef6545b1eef","abstract_canon_sha256":"aaee0ed234d9648b54a787322ecf1306e9f99e00facac51c1230923cf51ef4c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:06.434078Z","signature_b64":"Vn9AKdm4vyNBXUQMVo0rYToljzvIcRnUQfEfB5NyTEEMHHryfyijY4Usvxz5y1Bf3iZxjlNu0G0IN1bs/j0RCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1c97204f25a02c545d1ead54827638f005e902107e6243a8b57f352eb6e1289","last_reissued_at":"2026-07-05T03:48:06.433587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:06.433587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Tight Can PAC-Bayes be in the Small Data Regime?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Andrew Y. K. Foong, David R. Burt, Richard E. Turner, Wessel P. Bruinsma","submitted_at":"2021-06-07T12:11:32Z","abstract_excerpt":"In this paper, we investigate the question: Given a small number of datapoints, for example N = 30, how tight can PAC-Bayes and test set bounds be made? For such small datasets, test set bounds adversely affect generalisation performance by withholding data from the training procedure. In this setting, PAC-Bayes bounds are especially attractive, due to their ability to use all the data to simultaneously learn a posterior and bound its generalisation risk. We focus on the case of i.i.d. data with a bounded loss and consider the generic PAC-Bayes theorem of Germain et al. While their theorem is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03542","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/2106.03542/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":"2106.03542","created_at":"2026-07-05T03:48:06.433638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03542v4","created_at":"2026-07-05T03:48:06.433638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03542","created_at":"2026-07-05T03:48:06.433638+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHEXEBHSLIBM","created_at":"2026-07-05T03:48:06.433638+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHEXEBHSLIBMKROR","created_at":"2026-07-05T03:48:06.433638+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHEXEBHS","created_at":"2026-07-05T03:48:06.433638+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/UHEXEBHSLIBMKROR5LKUQJ3DR4","json":"https://pith.science/pith/UHEXEBHSLIBMKROR5LKUQJ3DR4.json","graph_json":"https://pith.science/api/pith-number/UHEXEBHSLIBMKROR5LKUQJ3DR4/graph.json","events_json":"https://pith.science/api/pith-number/UHEXEBHSLIBMKROR5LKUQJ3DR4/events.json","paper":"https://pith.science/paper/UHEXEBHS"},"agent_actions":{"view_html":"https://pith.science/pith/UHEXEBHSLIBMKROR5LKUQJ3DR4","download_json":"https://pith.science/pith/UHEXEBHSLIBMKROR5LKUQJ3DR4.json","view_paper":"https://pith.science/paper/UHEXEBHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03542&json=true","fetch_graph":"https://pith.science/api/pith-number/UHEXEBHSLIBMKROR5LKUQJ3DR4/graph.json","fetch_events":"https://pith.science/api/pith-number/UHEXEBHSLIBMKROR5LKUQJ3DR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHEXEBHSLIBMKROR5LKUQJ3DR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHEXEBHSLIBMKROR5LKUQJ3DR4/action/storage_attestation","attest_author":"https://pith.science/pith/UHEXEBHSLIBMKROR5LKUQJ3DR4/action/author_attestation","sign_citation":"https://pith.science/pith/UHEXEBHSLIBMKROR5LKUQJ3DR4/action/citation_signature","submit_replication":"https://pith.science/pith/UHEXEBHSLIBMKROR5LKUQJ3DR4/action/replication_record"}},"created_at":"2026-07-05T03:48:06.433638+00:00","updated_at":"2026-07-05T03:48:06.433638+00:00"}