{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:DV6W4YMMKKPV4A3D6T5J22PQZM","short_pith_number":"pith:DV6W4YMM","schema_version":"1.0","canonical_sha256":"1d7d6e618c529f5e0363f4fa9d69f0cb3892dd9715fa8088ef1a0da3c18cbd04","source":{"kind":"arxiv","id":"1511.07948","version":1},"attestation_state":"computed","paper":{"title":"Learning Halfspaces and Neural Networks with Random Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Martin J. Wainwright, Michael I. Jordan, Yuchen Zhang","submitted_at":"2015-11-25T04:41:20Z","abstract_excerpt":"We study non-convex empirical risk minimization for learning halfspaces and neural networks. For loss functions that are $L$-Lipschitz continuous, we present algorithms to learn halfspaces and multi-layer neural networks that achieve arbitrarily small excess risk $\\epsilon>0$. The time complexity is polynomial in the input dimension $d$ and the sample size $n$, but exponential in the quantity $(L/\\epsilon^2)\\log(L/\\epsilon)$. These algorithms run multiple rounds of random initialization followed by arbitrary optimization steps. We further show that if the data is separable by some neural netwo"},"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":"1511.07948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-25T04:41:20Z","cross_cats_sorted":[],"title_canon_sha256":"f6be6a8dbeaa733e4265689cc076e8a39b7f1be0b87e1e897830c43dd584ef61","abstract_canon_sha256":"84f835a97d1cd9dd314d66d1d38b7b12922e3d572b39424b96e19a2722a52be2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:02.131666Z","signature_b64":"seAfd7/ABxKsrOJB3q75UTy1gfw12dVn7pDccfNAZFQ/L3L7zZ8VJsw8K2aYC3lMyQ2LId1KT5UoBU45jsn6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d7d6e618c529f5e0363f4fa9d69f0cb3892dd9715fa8088ef1a0da3c18cbd04","last_reissued_at":"2026-05-18T01:26:02.131025Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:02.131025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Halfspaces and Neural Networks with Random Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Martin J. Wainwright, Michael I. Jordan, Yuchen Zhang","submitted_at":"2015-11-25T04:41:20Z","abstract_excerpt":"We study non-convex empirical risk minimization for learning halfspaces and neural networks. For loss functions that are $L$-Lipschitz continuous, we present algorithms to learn halfspaces and multi-layer neural networks that achieve arbitrarily small excess risk $\\epsilon>0$. The time complexity is polynomial in the input dimension $d$ and the sample size $n$, but exponential in the quantity $(L/\\epsilon^2)\\log(L/\\epsilon)$. These algorithms run multiple rounds of random initialization followed by arbitrary optimization steps. We further show that if the data is separable by some neural netwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07948","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":"1511.07948","created_at":"2026-05-18T01:26:02.131112+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.07948v1","created_at":"2026-05-18T01:26:02.131112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07948","created_at":"2026-05-18T01:26:02.131112+00:00"},{"alias_kind":"pith_short_12","alias_value":"DV6W4YMMKKPV","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_16","alias_value":"DV6W4YMMKKPV4A3D","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_8","alias_value":"DV6W4YMM","created_at":"2026-05-18T12:29:17.054201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2401.01335","citing_title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM","json":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM.json","graph_json":"https://pith.science/api/pith-number/DV6W4YMMKKPV4A3D6T5J22PQZM/graph.json","events_json":"https://pith.science/api/pith-number/DV6W4YMMKKPV4A3D6T5J22PQZM/events.json","paper":"https://pith.science/paper/DV6W4YMM"},"agent_actions":{"view_html":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM","download_json":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM.json","view_paper":"https://pith.science/paper/DV6W4YMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.07948&json=true","fetch_graph":"https://pith.science/api/pith-number/DV6W4YMMKKPV4A3D6T5J22PQZM/graph.json","fetch_events":"https://pith.science/api/pith-number/DV6W4YMMKKPV4A3D6T5J22PQZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM/action/storage_attestation","attest_author":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM/action/author_attestation","sign_citation":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM/action/citation_signature","submit_replication":"https://pith.science/pith/DV6W4YMMKKPV4A3D6T5J22PQZM/action/replication_record"}},"created_at":"2026-05-18T01:26:02.131112+00:00","updated_at":"2026-05-18T01:26:02.131112+00:00"}