{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PDVGPKJBYOAD6WBUDI7I4I7ACA","short_pith_number":"pith:PDVGPKJB","schema_version":"1.0","canonical_sha256":"78ea67a921c3803f58341a3e8e23e01033be383f2be2fdfda10f8c63e15d82c6","source":{"kind":"arxiv","id":"2411.01088","version":1},"attestation_state":"computed","paper":{"title":"CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Mert Pilanci, Miria Feng, Zachary Frangella","submitted_at":"2024-11-02T00:18:59Z","abstract_excerpt":"We introduce the CRONOS algorithm for convex optimization of two-layer neural networks. CRONOS is the first algorithm capable of scaling to high-dimensional datasets such as ImageNet, which are ubiquitous in modern deep learning. This significantly improves upon prior work, which has been restricted to downsampled versions of MNIST and CIFAR-10. Taking CRONOS as a primitive, we then develop a new algorithm called CRONOS-AM, which combines CRONOS with alternating minimization, to obtain an algorithm capable of training multi-layer networks with arbitrary architectures. Our theoretical analysis "},"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":"2411.01088","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-02T00:18:59Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"1b1a6f55c7bf8ed646e3a93875c12e491dfcca4a85b931cd3ca4dd1db8fb6f7d","abstract_canon_sha256":"ddfe9a87c6b0bba077729d2b8de7f0b253cd46d55cc6310349250ca73faf753a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:01.621468Z","signature_b64":"b4bGb+4YgVwod+GrdBRfQ1imAVszFNH14rVZ/aP5U0sHxc1rWXSX2Nmpt8Vq5l4gH3pl6GPgP7xFU0uWGnv1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78ea67a921c3803f58341a3e8e23e01033be383f2be2fdfda10f8c63e15d82c6","last_reissued_at":"2026-05-25T02:01:01.620560Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:01.620560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Mert Pilanci, Miria Feng, Zachary Frangella","submitted_at":"2024-11-02T00:18:59Z","abstract_excerpt":"We introduce the CRONOS algorithm for convex optimization of two-layer neural networks. CRONOS is the first algorithm capable of scaling to high-dimensional datasets such as ImageNet, which are ubiquitous in modern deep learning. This significantly improves upon prior work, which has been restricted to downsampled versions of MNIST and CIFAR-10. Taking CRONOS as a primitive, we then develop a new algorithm called CRONOS-AM, which combines CRONOS with alternating minimization, to obtain an algorithm capable of training multi-layer networks with arbitrary architectures. Our theoretical analysis "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01088","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/2411.01088/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":"2411.01088","created_at":"2026-05-25T02:01:01.620691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01088v1","created_at":"2026-05-25T02:01:01.620691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01088","created_at":"2026-05-25T02:01:01.620691+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDVGPKJBYOAD","created_at":"2026-05-25T02:01:01.620691+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDVGPKJBYOAD6WBU","created_at":"2026-05-25T02:01:01.620691+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDVGPKJB","created_at":"2026-05-25T02:01:01.620691+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/PDVGPKJBYOAD6WBUDI7I4I7ACA","json":"https://pith.science/pith/PDVGPKJBYOAD6WBUDI7I4I7ACA.json","graph_json":"https://pith.science/api/pith-number/PDVGPKJBYOAD6WBUDI7I4I7ACA/graph.json","events_json":"https://pith.science/api/pith-number/PDVGPKJBYOAD6WBUDI7I4I7ACA/events.json","paper":"https://pith.science/paper/PDVGPKJB"},"agent_actions":{"view_html":"https://pith.science/pith/PDVGPKJBYOAD6WBUDI7I4I7ACA","download_json":"https://pith.science/pith/PDVGPKJBYOAD6WBUDI7I4I7ACA.json","view_paper":"https://pith.science/paper/PDVGPKJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01088&json=true","fetch_graph":"https://pith.science/api/pith-number/PDVGPKJBYOAD6WBUDI7I4I7ACA/graph.json","fetch_events":"https://pith.science/api/pith-number/PDVGPKJBYOAD6WBUDI7I4I7ACA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDVGPKJBYOAD6WBUDI7I4I7ACA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDVGPKJBYOAD6WBUDI7I4I7ACA/action/storage_attestation","attest_author":"https://pith.science/pith/PDVGPKJBYOAD6WBUDI7I4I7ACA/action/author_attestation","sign_citation":"https://pith.science/pith/PDVGPKJBYOAD6WBUDI7I4I7ACA/action/citation_signature","submit_replication":"https://pith.science/pith/PDVGPKJBYOAD6WBUDI7I4I7ACA/action/replication_record"}},"created_at":"2026-05-25T02:01:01.620691+00:00","updated_at":"2026-05-25T02:01:01.620691+00:00"}