{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PRP5EJO7LTDLNYEYM3YEGPN6UC","short_pith_number":"pith:PRP5EJO7","schema_version":"1.0","canonical_sha256":"7c5fd225df5cc6b6e09866f0433dbea0be72adefcbf23b760de49e38bb4763d9","source":{"kind":"arxiv","id":"2302.11709","version":1},"attestation_state":"computed","paper":{"title":"Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Badr-Eddine Ch\\'erief-Abdellatif, Charles Riou, Pierre Alquier","submitted_at":"2023-02-23T00:07:03Z","abstract_excerpt":"Bernstein's condition is a key assumption that guarantees fast rates in machine learning. For example, the Gibbs algorithm with prior $\\pi$ has an excess risk in $O(d_{\\pi}/n)$, as opposed to the standard $O(\\sqrt{d_{\\pi}/n})$, where $n$ denotes the number of observations and $d_{\\pi}$ is a complexity parameter which depends on the prior $\\pi$. In this paper, we examine the Gibbs algorithm in the context of meta-learning, i.e., when learning the prior $\\pi$ from $T$ tasks (with $n$ observations each) generated by a meta distribution. Our main result is that Bernstein's condition always holds a"},"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":"2302.11709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-02-23T00:07:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"493e20a69200aa383c8193932772ec357c18ad1e975716b3984f984ce7243a89","abstract_canon_sha256":"281e37a3d013c19f148fa953c90f8cb8264ed293ad7cf4ad732a583228a1edfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:15.716466Z","signature_b64":"OxV8OMR9dISMYJ0qXZmjDWHdi+jmxZLoAGDGXu4e5cHUuij9IVUJCjzpNtFabrA+htkgkRi8jxyqcL+Cy3lTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c5fd225df5cc6b6e09866f0433dbea0be72adefcbf23b760de49e38bb4763d9","last_reissued_at":"2026-07-05T10:21:15.716000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:15.716000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Badr-Eddine Ch\\'erief-Abdellatif, Charles Riou, Pierre Alquier","submitted_at":"2023-02-23T00:07:03Z","abstract_excerpt":"Bernstein's condition is a key assumption that guarantees fast rates in machine learning. For example, the Gibbs algorithm with prior $\\pi$ has an excess risk in $O(d_{\\pi}/n)$, as opposed to the standard $O(\\sqrt{d_{\\pi}/n})$, where $n$ denotes the number of observations and $d_{\\pi}$ is a complexity parameter which depends on the prior $\\pi$. In this paper, we examine the Gibbs algorithm in the context of meta-learning, i.e., when learning the prior $\\pi$ from $T$ tasks (with $n$ observations each) generated by a meta distribution. Our main result is that Bernstein's condition always holds a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11709","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/2302.11709/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":"2302.11709","created_at":"2026-07-05T10:21:15.716051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.11709v1","created_at":"2026-07-05T10:21:15.716051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11709","created_at":"2026-07-05T10:21:15.716051+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRP5EJO7LTDL","created_at":"2026-07-05T10:21:15.716051+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRP5EJO7LTDLNYEY","created_at":"2026-07-05T10:21:15.716051+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRP5EJO7","created_at":"2026-07-05T10:21:15.716051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.19067","citing_title":"From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRP5EJO7LTDLNYEYM3YEGPN6UC","json":"https://pith.science/pith/PRP5EJO7LTDLNYEYM3YEGPN6UC.json","graph_json":"https://pith.science/api/pith-number/PRP5EJO7LTDLNYEYM3YEGPN6UC/graph.json","events_json":"https://pith.science/api/pith-number/PRP5EJO7LTDLNYEYM3YEGPN6UC/events.json","paper":"https://pith.science/paper/PRP5EJO7"},"agent_actions":{"view_html":"https://pith.science/pith/PRP5EJO7LTDLNYEYM3YEGPN6UC","download_json":"https://pith.science/pith/PRP5EJO7LTDLNYEYM3YEGPN6UC.json","view_paper":"https://pith.science/paper/PRP5EJO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.11709&json=true","fetch_graph":"https://pith.science/api/pith-number/PRP5EJO7LTDLNYEYM3YEGPN6UC/graph.json","fetch_events":"https://pith.science/api/pith-number/PRP5EJO7LTDLNYEYM3YEGPN6UC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRP5EJO7LTDLNYEYM3YEGPN6UC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRP5EJO7LTDLNYEYM3YEGPN6UC/action/storage_attestation","attest_author":"https://pith.science/pith/PRP5EJO7LTDLNYEYM3YEGPN6UC/action/author_attestation","sign_citation":"https://pith.science/pith/PRP5EJO7LTDLNYEYM3YEGPN6UC/action/citation_signature","submit_replication":"https://pith.science/pith/PRP5EJO7LTDLNYEYM3YEGPN6UC/action/replication_record"}},"created_at":"2026-07-05T10:21:15.716051+00:00","updated_at":"2026-07-05T10:21:15.716051+00:00"}