{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TTF7RURGAAIUOONXEY576O6B4P","short_pith_number":"pith:TTF7RURG","schema_version":"1.0","canonical_sha256":"9ccbf8d22600114739b7263bff3bc1e3fa0accc9e18a20ea577361e11efb0ae6","source":{"kind":"arxiv","id":"1711.07354","version":1},"attestation_state":"computed","paper":{"title":"Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Matthew Brand, Ziming Zhang","submitted_at":"2017-11-20T15:04:45Z","abstract_excerpt":"By lifting the ReLU function into a higher dimensional space, we develop a smooth multi-convex formulation for training feed-forward deep neural networks (DNNs). This allows us to develop a block coordinate descent (BCD) training algorithm consisting of a sequence of numerically well-behaved convex optimizations. Using ideas from proximal point methods in convex analysis, we prove that this BCD algorithm will converge globally to a stationary point with R-linear convergence rate of order one. In experiments with the MNIST database, DNNs trained with this BCD algorithm consistently yielded bett"},"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":"1711.07354","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-20T15:04:45Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"4704745446561e046e2ff93e0ba517fbac3cee94ae6732791c1636e2884e6c8b","abstract_canon_sha256":"ce1049240a710bf8b6438a9f8f33c0de5f135e11f0cdb2702eb23cd4eea50ab9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:10.371996Z","signature_b64":"IhTbEfQFhDKDSF7Z/Uz4+vfH4UnGVT9bERXI7KP3XiusVRY4cOGA4aFoqm07h4kfheHUjc6moKwyp6O5nIg9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ccbf8d22600114739b7263bff3bc1e3fa0accc9e18a20ea577361e11efb0ae6","last_reissued_at":"2026-05-18T00:30:10.371309Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:10.371309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Matthew Brand, Ziming Zhang","submitted_at":"2017-11-20T15:04:45Z","abstract_excerpt":"By lifting the ReLU function into a higher dimensional space, we develop a smooth multi-convex formulation for training feed-forward deep neural networks (DNNs). This allows us to develop a block coordinate descent (BCD) training algorithm consisting of a sequence of numerically well-behaved convex optimizations. Using ideas from proximal point methods in convex analysis, we prove that this BCD algorithm will converge globally to a stationary point with R-linear convergence rate of order one. In experiments with the MNIST database, DNNs trained with this BCD algorithm consistently yielded bett"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07354","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":"1711.07354","created_at":"2026-05-18T00:30:10.371433+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.07354v1","created_at":"2026-05-18T00:30:10.371433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07354","created_at":"2026-05-18T00:30:10.371433+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTF7RURGAAIU","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTF7RURGAAIUOONX","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTF7RURG","created_at":"2026-05-18T12:31:46.661854+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/TTF7RURGAAIUOONXEY576O6B4P","json":"https://pith.science/pith/TTF7RURGAAIUOONXEY576O6B4P.json","graph_json":"https://pith.science/api/pith-number/TTF7RURGAAIUOONXEY576O6B4P/graph.json","events_json":"https://pith.science/api/pith-number/TTF7RURGAAIUOONXEY576O6B4P/events.json","paper":"https://pith.science/paper/TTF7RURG"},"agent_actions":{"view_html":"https://pith.science/pith/TTF7RURGAAIUOONXEY576O6B4P","download_json":"https://pith.science/pith/TTF7RURGAAIUOONXEY576O6B4P.json","view_paper":"https://pith.science/paper/TTF7RURG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.07354&json=true","fetch_graph":"https://pith.science/api/pith-number/TTF7RURGAAIUOONXEY576O6B4P/graph.json","fetch_events":"https://pith.science/api/pith-number/TTF7RURGAAIUOONXEY576O6B4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTF7RURGAAIUOONXEY576O6B4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTF7RURGAAIUOONXEY576O6B4P/action/storage_attestation","attest_author":"https://pith.science/pith/TTF7RURGAAIUOONXEY576O6B4P/action/author_attestation","sign_citation":"https://pith.science/pith/TTF7RURGAAIUOONXEY576O6B4P/action/citation_signature","submit_replication":"https://pith.science/pith/TTF7RURGAAIUOONXEY576O6B4P/action/replication_record"}},"created_at":"2026-05-18T00:30:10.371433+00:00","updated_at":"2026-05-18T00:30:10.371433+00:00"}