{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5N2FP47KTAP3TWJTUWHS3XBETO","short_pith_number":"pith:5N2FP47K","schema_version":"1.0","canonical_sha256":"eb7457f3ea981fb9d933a58f2ddc249ba37b3f09707a99579e390b84ee1fdce4","source":{"kind":"arxiv","id":"1710.08402","version":1},"attestation_state":"computed","paper":{"title":"Stability and Generalization of Learning Algorithms that Converge to Global Optima","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","math.OC"],"primary_cat":"stat.ML","authors_text":"Dimitris Papailiopoulos, Zachary Charles","submitted_at":"2017-10-23T17:42:30Z","abstract_excerpt":"We establish novel generalization bounds for learning algorithms that converge to global minima. We do so by deriving black-box stability results that only depend on the convergence of a learning algorithm and the geometry around the minimizers of the loss function. The results are shown for nonconvex loss functions satisfying the Polyak-{\\L}ojasiewicz (PL) and the quadratic growth (QG) conditions. We further show that these conditions arise for some neural networks with linear activations. We use our black-box results to establish the stability of optimization algorithms such as stochastic gr"},"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":"1710.08402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-23T17:42:30Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.OC"],"title_canon_sha256":"be94cb9184cee522a394f6f646d6fefad6d7d972890d51090d27d98e3c68f2be","abstract_canon_sha256":"d39745019d3e4bf2d5f9a76e3e4b0a7dd8dc180adf85006b4c3e83d5d630be70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:16.119542Z","signature_b64":"NXAElBS60BV9pZBRXywTtYHQ1SvCxlneCkYk0u+asunfpfFkyyfn7qb5zePCHnSd3CLFthWQWlmKojTTL//8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb7457f3ea981fb9d933a58f2ddc249ba37b3f09707a99579e390b84ee1fdce4","last_reissued_at":"2026-05-18T00:32:16.118741Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:16.118741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stability and Generalization of Learning Algorithms that Converge to Global Optima","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","math.OC"],"primary_cat":"stat.ML","authors_text":"Dimitris Papailiopoulos, Zachary Charles","submitted_at":"2017-10-23T17:42:30Z","abstract_excerpt":"We establish novel generalization bounds for learning algorithms that converge to global minima. We do so by deriving black-box stability results that only depend on the convergence of a learning algorithm and the geometry around the minimizers of the loss function. The results are shown for nonconvex loss functions satisfying the Polyak-{\\L}ojasiewicz (PL) and the quadratic growth (QG) conditions. We further show that these conditions arise for some neural networks with linear activations. We use our black-box results to establish the stability of optimization algorithms such as stochastic gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.08402","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":""},"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":"1710.08402","created_at":"2026-05-18T00:32:16.118856+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.08402v1","created_at":"2026-05-18T00:32:16.118856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.08402","created_at":"2026-05-18T00:32:16.118856+00:00"},{"alias_kind":"pith_short_12","alias_value":"5N2FP47KTAP3","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"5N2FP47KTAP3TWJT","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"5N2FP47K","created_at":"2026-05-18T12:31:00.734936+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/5N2FP47KTAP3TWJTUWHS3XBETO","json":"https://pith.science/pith/5N2FP47KTAP3TWJTUWHS3XBETO.json","graph_json":"https://pith.science/api/pith-number/5N2FP47KTAP3TWJTUWHS3XBETO/graph.json","events_json":"https://pith.science/api/pith-number/5N2FP47KTAP3TWJTUWHS3XBETO/events.json","paper":"https://pith.science/paper/5N2FP47K"},"agent_actions":{"view_html":"https://pith.science/pith/5N2FP47KTAP3TWJTUWHS3XBETO","download_json":"https://pith.science/pith/5N2FP47KTAP3TWJTUWHS3XBETO.json","view_paper":"https://pith.science/paper/5N2FP47K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.08402&json=true","fetch_graph":"https://pith.science/api/pith-number/5N2FP47KTAP3TWJTUWHS3XBETO/graph.json","fetch_events":"https://pith.science/api/pith-number/5N2FP47KTAP3TWJTUWHS3XBETO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5N2FP47KTAP3TWJTUWHS3XBETO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5N2FP47KTAP3TWJTUWHS3XBETO/action/storage_attestation","attest_author":"https://pith.science/pith/5N2FP47KTAP3TWJTUWHS3XBETO/action/author_attestation","sign_citation":"https://pith.science/pith/5N2FP47KTAP3TWJTUWHS3XBETO/action/citation_signature","submit_replication":"https://pith.science/pith/5N2FP47KTAP3TWJTUWHS3XBETO/action/replication_record"}},"created_at":"2026-05-18T00:32:16.118856+00:00","updated_at":"2026-05-18T00:32:16.118856+00:00"}