{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UFSZ6VKEEJIRX7ZAJSAGUS6EY5","short_pith_number":"pith:UFSZ6VKE","schema_version":"1.0","canonical_sha256":"a1659f554422511bff204c806a4bc4c771eff1001ce9d28b0279c77a5cd23290","source":{"kind":"arxiv","id":"1901.08584","version":2},"attestation_state":"computed","paper":{"title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ruosong Wang, Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li","submitted_at":"2019-01-24T18:58:16Z","abstract_excerpt":"Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and provides the following improvements over recent works:\n  (i) Using a tighter characterization of training speed than recent papers, an explanation for why training a neural net with random labels leads to slower training, as originally observed in [Zhang et al. ICLR'17].\n  (ii) Generalization bound independent of network size, using a data-dependent complex"},"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":"1901.08584","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T18:58:16Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"8ebd74eb336e31683b2e5d0af42d3a591599fe1457add05e813802309fa1a4fe","abstract_canon_sha256":"09a6654a65139287ab24950eb63fd96f161392531247430a7ef4c61c96146f19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:04.065619Z","signature_b64":"B+qF8F7bFcssoOhmUhwYBxGUKI2NkdhuYEhBN061sgpVaCMt0CtHuEd5B1R2xSStCzUGrsozC0gTcBlgBHcGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1659f554422511bff204c806a4bc4c771eff1001ce9d28b0279c77a5cd23290","last_reissued_at":"2026-05-17T23:45:04.065004Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:04.065004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ruosong Wang, Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li","submitted_at":"2019-01-24T18:58:16Z","abstract_excerpt":"Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and provides the following improvements over recent works:\n  (i) Using a tighter characterization of training speed than recent papers, an explanation for why training a neural net with random labels leads to slower training, as originally observed in [Zhang et al. ICLR'17].\n  (ii) Generalization bound independent of network size, using a data-dependent complex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08584","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":"1901.08584","created_at":"2026-05-17T23:45:04.065089+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08584v2","created_at":"2026-05-17T23:45:04.065089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08584","created_at":"2026-05-17T23:45:04.065089+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFSZ6VKEEJIR","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFSZ6VKEEJIRX7ZA","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFSZ6VKE","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.08654","citing_title":"ID3 Learns Juntas for Smoothed Product Distributions","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00560","citing_title":"On Symmetry and Initialization for Neural Networks","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18673","citing_title":"Neural Networks Reveal a Universal Bias in Conformal Correlators","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFSZ6VKEEJIRX7ZAJSAGUS6EY5","json":"https://pith.science/pith/UFSZ6VKEEJIRX7ZAJSAGUS6EY5.json","graph_json":"https://pith.science/api/pith-number/UFSZ6VKEEJIRX7ZAJSAGUS6EY5/graph.json","events_json":"https://pith.science/api/pith-number/UFSZ6VKEEJIRX7ZAJSAGUS6EY5/events.json","paper":"https://pith.science/paper/UFSZ6VKE"},"agent_actions":{"view_html":"https://pith.science/pith/UFSZ6VKEEJIRX7ZAJSAGUS6EY5","download_json":"https://pith.science/pith/UFSZ6VKEEJIRX7ZAJSAGUS6EY5.json","view_paper":"https://pith.science/paper/UFSZ6VKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08584&json=true","fetch_graph":"https://pith.science/api/pith-number/UFSZ6VKEEJIRX7ZAJSAGUS6EY5/graph.json","fetch_events":"https://pith.science/api/pith-number/UFSZ6VKEEJIRX7ZAJSAGUS6EY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFSZ6VKEEJIRX7ZAJSAGUS6EY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFSZ6VKEEJIRX7ZAJSAGUS6EY5/action/storage_attestation","attest_author":"https://pith.science/pith/UFSZ6VKEEJIRX7ZAJSAGUS6EY5/action/author_attestation","sign_citation":"https://pith.science/pith/UFSZ6VKEEJIRX7ZAJSAGUS6EY5/action/citation_signature","submit_replication":"https://pith.science/pith/UFSZ6VKEEJIRX7ZAJSAGUS6EY5/action/replication_record"}},"created_at":"2026-05-17T23:45:04.065089+00:00","updated_at":"2026-05-17T23:45:04.065089+00:00"}