{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PDVGPKJBYOAD6WBUDI7I4I7ACA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ddfe9a87c6b0bba077729d2b8de7f0b253cd46d55cc6310349250ca73faf753a","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-02T00:18:59Z","title_canon_sha256":"1b1a6f55c7bf8ed646e3a93875c12e491dfcca4a85b931cd3ca4dd1db8fb6f7d"},"schema_version":"1.0","source":{"id":"2411.01088","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01088","created_at":"2026-05-25T02:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01088v1","created_at":"2026-05-25T02:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01088","created_at":"2026-05-25T02:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"PDVGPKJBYOAD","created_at":"2026-05-25T02:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"PDVGPKJBYOAD6WBU","created_at":"2026-05-25T02:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"PDVGPKJB","created_at":"2026-05-25T02:01:01Z"}],"graph_snapshots":[{"event_id":"sha256:8695e0105e39f5927310441152108e010ce6707bf97f72bdee2e1126f60280f8","target":"graph","created_at":"2026-05-25T02:01:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.01088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Mert Pilanci, Miria Feng, Zachary Frangella","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-02T00:18:59Z","title":"CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01088","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:aa93f5515316f166e66b6336c2e7b38006040a00784f1e481093fe56a4e7522e","target":"record","created_at":"2026-05-25T02:01:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ddfe9a87c6b0bba077729d2b8de7f0b253cd46d55cc6310349250ca73faf753a","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-02T00:18:59Z","title_canon_sha256":"1b1a6f55c7bf8ed646e3a93875c12e491dfcca4a85b931cd3ca4dd1db8fb6f7d"},"schema_version":"1.0","source":{"id":"2411.01088","kind":"arxiv","version":1}},"canonical_sha256":"78ea67a921c3803f58341a3e8e23e01033be383f2be2fdfda10f8c63e15d82c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78ea67a921c3803f58341a3e8e23e01033be383f2be2fdfda10f8c63e15d82c6","first_computed_at":"2026-05-25T02:01:01.620560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:01.620560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b4bGb+4YgVwod+GrdBRfQ1imAVszFNH14rVZ/aP5U0sHxc1rWXSX2Nmpt8Vq5l4gH3pl6GPgP7xFU0uWGnv1CA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:01.621468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01088","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa93f5515316f166e66b6336c2e7b38006040a00784f1e481093fe56a4e7522e","sha256:8695e0105e39f5927310441152108e010ce6707bf97f72bdee2e1126f60280f8"],"state_sha256":"ed0df21b3eb923e251d7396807a1cc55399aad02ee4d78192f989e33c882f4cf"}