{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SZRLVZHHKMCQKSBKBHWOENXAO3","short_pith_number":"pith:SZRLVZHH","schema_version":"1.0","canonical_sha256":"9662bae4e7530505482a09ece236e076ecf23099b4ab8e1969cfe4607134ae42","source":{"kind":"arxiv","id":"1812.09859","version":2},"attestation_state":"computed","paper":{"title":"Generalization Bounds for Uniformly Stable Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jan Vondrak, Vitaly Feldman","submitted_at":"2018-12-24T07:55:45Z","abstract_excerpt":"Uniform stability of a learning algorithm is a classical notion of algorithmic stability introduced to derive high-probability bounds on the generalization error (Bousquet and Elisseeff, 2002). Specifically, for a loss function with range bounded in $[0,1]$, the generalization error of a $\\gamma$-uniformly stable learning algorithm on $n$ samples is known to be within $O((\\gamma +1/n) \\sqrt{n \\log(1/\\delta)})$ of the empirical error with probability at least $1-\\delta$. Unfortunately, this bound does not lead to meaningful generalization bounds in many common settings where $\\gamma \\geq 1/\\sqr"},"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":"1812.09859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-24T07:55:45Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"b25f96d771e5c9d373f70174e71bd8ba262339afc3b04df393f807322f8ad1fe","abstract_canon_sha256":"32b229476bf4e99d9966c784bbda0f93a8104c89237eb9163d2432fd585b85a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:05.125082Z","signature_b64":"XyaayiMNsnXuGb5wq879P4Mtoe0d38qzjol0mf+ctTZtdCgMoJq+sSRyVLFFaMZTIzW2evKmWdqBgtEYppNBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9662bae4e7530505482a09ece236e076ecf23099b4ab8e1969cfe4607134ae42","last_reissued_at":"2026-05-17T23:51:05.124472Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:05.124472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization Bounds for Uniformly Stable Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jan Vondrak, Vitaly Feldman","submitted_at":"2018-12-24T07:55:45Z","abstract_excerpt":"Uniform stability of a learning algorithm is a classical notion of algorithmic stability introduced to derive high-probability bounds on the generalization error (Bousquet and Elisseeff, 2002). Specifically, for a loss function with range bounded in $[0,1]$, the generalization error of a $\\gamma$-uniformly stable learning algorithm on $n$ samples is known to be within $O((\\gamma +1/n) \\sqrt{n \\log(1/\\delta)})$ of the empirical error with probability at least $1-\\delta$. Unfortunately, this bound does not lead to meaningful generalization bounds in many common settings where $\\gamma \\geq 1/\\sqr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09859","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":""},"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":"1812.09859","created_at":"2026-05-17T23:51:05.124559+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.09859v2","created_at":"2026-05-17T23:51:05.124559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09859","created_at":"2026-05-17T23:51:05.124559+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZRLVZHHKMCQ","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZRLVZHHKMCQKSBK","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZRLVZHH","created_at":"2026-05-18T12:32:53.628368+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/SZRLVZHHKMCQKSBKBHWOENXAO3","json":"https://pith.science/pith/SZRLVZHHKMCQKSBKBHWOENXAO3.json","graph_json":"https://pith.science/api/pith-number/SZRLVZHHKMCQKSBKBHWOENXAO3/graph.json","events_json":"https://pith.science/api/pith-number/SZRLVZHHKMCQKSBKBHWOENXAO3/events.json","paper":"https://pith.science/paper/SZRLVZHH"},"agent_actions":{"view_html":"https://pith.science/pith/SZRLVZHHKMCQKSBKBHWOENXAO3","download_json":"https://pith.science/pith/SZRLVZHHKMCQKSBKBHWOENXAO3.json","view_paper":"https://pith.science/paper/SZRLVZHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.09859&json=true","fetch_graph":"https://pith.science/api/pith-number/SZRLVZHHKMCQKSBKBHWOENXAO3/graph.json","fetch_events":"https://pith.science/api/pith-number/SZRLVZHHKMCQKSBKBHWOENXAO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZRLVZHHKMCQKSBKBHWOENXAO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZRLVZHHKMCQKSBKBHWOENXAO3/action/storage_attestation","attest_author":"https://pith.science/pith/SZRLVZHHKMCQKSBKBHWOENXAO3/action/author_attestation","sign_citation":"https://pith.science/pith/SZRLVZHHKMCQKSBKBHWOENXAO3/action/citation_signature","submit_replication":"https://pith.science/pith/SZRLVZHHKMCQKSBKBHWOENXAO3/action/replication_record"}},"created_at":"2026-05-17T23:51:05.124559+00:00","updated_at":"2026-05-17T23:51:05.124559+00:00"}