{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:L5HM3CEPDKVMKG2ZQHLU3KJNUI","short_pith_number":"pith:L5HM3CEP","schema_version":"1.0","canonical_sha256":"5f4ecd888f1aaac51b5981d74da92da23bdaf8c19fb96561c6bbb86c09b458fa","source":{"kind":"arxiv","id":"1605.02026","version":1},"attestation_state":"computed","paper":{"title":"Training Neural Networks Without Gradients: A Scalable ADMM Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ankit Patel, Bharat Singh, Gavin Taylor, Ryan Burmeister, Tom Goldstein, Zheng Xu","submitted_at":"2016-05-06T18:38:45Z","abstract_excerpt":"With the growing importance of large network models and enormous training datasets, GPUs have become increasingly necessary to train neural networks. This is largely because conventional optimization algorithms rely on stochastic gradient methods that don't scale well to large numbers of cores in a cluster setting. Furthermore, the convergence of all gradient methods, including batch methods, suffers from common problems like saturation effects, poor conditioning, and saddle points. This paper explores an unconventional training method that uses alternating direction methods and Bregman iterat"},"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":"1605.02026","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-06T18:38:45Z","cross_cats_sorted":[],"title_canon_sha256":"6026f539cecf6d32b2dbd470cbf676547194a13a21602d05fab3605e9029c4ca","abstract_canon_sha256":"839755b422d9b3c3f5acb1a2a63ffabd2ee335af4d6441757d53aa8ff0125357"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:30.590559Z","signature_b64":"MfLgDY+QbZ9cIgjoRDEKdYun6xXEAEz+5UyGgQYM3mjs0sgZPMLDWBq+ML057+9WF2RjFaGqjMmOThCkYbVfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f4ecd888f1aaac51b5981d74da92da23bdaf8c19fb96561c6bbb86c09b458fa","last_reissued_at":"2026-05-18T01:15:30.589828Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:30.589828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Neural Networks Without Gradients: A Scalable ADMM Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ankit Patel, Bharat Singh, Gavin Taylor, Ryan Burmeister, Tom Goldstein, Zheng Xu","submitted_at":"2016-05-06T18:38:45Z","abstract_excerpt":"With the growing importance of large network models and enormous training datasets, GPUs have become increasingly necessary to train neural networks. This is largely because conventional optimization algorithms rely on stochastic gradient methods that don't scale well to large numbers of cores in a cluster setting. Furthermore, the convergence of all gradient methods, including batch methods, suffers from common problems like saturation effects, poor conditioning, and saddle points. This paper explores an unconventional training method that uses alternating direction methods and Bregman iterat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.02026","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":"1605.02026","created_at":"2026-05-18T01:15:30.589954+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.02026v1","created_at":"2026-05-18T01:15:30.589954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.02026","created_at":"2026-05-18T01:15:30.589954+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5HM3CEPDKVM","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5HM3CEPDKVMKG2Z","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5HM3CEP","created_at":"2026-05-18T12:30:29.479603+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/L5HM3CEPDKVMKG2ZQHLU3KJNUI","json":"https://pith.science/pith/L5HM3CEPDKVMKG2ZQHLU3KJNUI.json","graph_json":"https://pith.science/api/pith-number/L5HM3CEPDKVMKG2ZQHLU3KJNUI/graph.json","events_json":"https://pith.science/api/pith-number/L5HM3CEPDKVMKG2ZQHLU3KJNUI/events.json","paper":"https://pith.science/paper/L5HM3CEP"},"agent_actions":{"view_html":"https://pith.science/pith/L5HM3CEPDKVMKG2ZQHLU3KJNUI","download_json":"https://pith.science/pith/L5HM3CEPDKVMKG2ZQHLU3KJNUI.json","view_paper":"https://pith.science/paper/L5HM3CEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.02026&json=true","fetch_graph":"https://pith.science/api/pith-number/L5HM3CEPDKVMKG2ZQHLU3KJNUI/graph.json","fetch_events":"https://pith.science/api/pith-number/L5HM3CEPDKVMKG2ZQHLU3KJNUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5HM3CEPDKVMKG2ZQHLU3KJNUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5HM3CEPDKVMKG2ZQHLU3KJNUI/action/storage_attestation","attest_author":"https://pith.science/pith/L5HM3CEPDKVMKG2ZQHLU3KJNUI/action/author_attestation","sign_citation":"https://pith.science/pith/L5HM3CEPDKVMKG2ZQHLU3KJNUI/action/citation_signature","submit_replication":"https://pith.science/pith/L5HM3CEPDKVMKG2ZQHLU3KJNUI/action/replication_record"}},"created_at":"2026-05-18T01:15:30.589954+00:00","updated_at":"2026-05-18T01:15:30.589954+00:00"}