{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OIAZHYZMDO65IVDCAR7W4AF3GI","short_pith_number":"pith:OIAZHYZM","schema_version":"1.0","canonical_sha256":"720193e32c1bbdd45462047f6e00bb322b25e019f8ca85ff71251fd1dc283d1b","source":{"kind":"arxiv","id":"1803.09082","version":1},"attestation_state":"computed","paper":{"title":"A Proximal Block Coordinate Descent Algorithm for Deep Neural Network Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Baoyuan Wu, Jinshan Zeng, Tim Tsz-Kit Lau, Yuan Yao","submitted_at":"2018-03-24T09:17:27Z","abstract_excerpt":"Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization. The backpropagation (backprop) algorithm has long been the most widely used algorithm for gradient computation of parameters of DNNs and is used along with gradient descent-type algorithms for this optimization task. Recent work have shown the efficiency of block coordinate descent (BCD) type methods empirically for training DNNs. In view of this, we propose a novel algorithm based on the BCD method for training DNNs and provide its global convergence results built upon the powe"},"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":"1803.09082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-24T09:17:27Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"d53dc44d58336b39b76177631fba90fb0307a7235129d654570af2fcce3f3e7d","abstract_canon_sha256":"f48580aae14ad9cf0625251efd30d11a7472ab29155b1f5dd05cafc571e186f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:12.660387Z","signature_b64":"m+HdLjHU193ejGGEXXcOf+Fu75imZ/7nIrD6Ev5FWz8S9q99UoKLEo2FRKKGRfItSqKBru+w1BSTy9xt3BRpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"720193e32c1bbdd45462047f6e00bb322b25e019f8ca85ff71251fd1dc283d1b","last_reissued_at":"2026-05-18T00:20:12.659929Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:12.659929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Proximal Block Coordinate Descent Algorithm for Deep Neural Network Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Baoyuan Wu, Jinshan Zeng, Tim Tsz-Kit Lau, Yuan Yao","submitted_at":"2018-03-24T09:17:27Z","abstract_excerpt":"Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization. The backpropagation (backprop) algorithm has long been the most widely used algorithm for gradient computation of parameters of DNNs and is used along with gradient descent-type algorithms for this optimization task. Recent work have shown the efficiency of block coordinate descent (BCD) type methods empirically for training DNNs. In view of this, we propose a novel algorithm based on the BCD method for training DNNs and provide its global convergence results built upon the powe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09082","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":"1803.09082","created_at":"2026-05-18T00:20:12.660008+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.09082v1","created_at":"2026-05-18T00:20:12.660008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09082","created_at":"2026-05-18T00:20:12.660008+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIAZHYZMDO65","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIAZHYZMDO65IVDC","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIAZHYZM","created_at":"2026-05-18T12:32:43.782077+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/OIAZHYZMDO65IVDCAR7W4AF3GI","json":"https://pith.science/pith/OIAZHYZMDO65IVDCAR7W4AF3GI.json","graph_json":"https://pith.science/api/pith-number/OIAZHYZMDO65IVDCAR7W4AF3GI/graph.json","events_json":"https://pith.science/api/pith-number/OIAZHYZMDO65IVDCAR7W4AF3GI/events.json","paper":"https://pith.science/paper/OIAZHYZM"},"agent_actions":{"view_html":"https://pith.science/pith/OIAZHYZMDO65IVDCAR7W4AF3GI","download_json":"https://pith.science/pith/OIAZHYZMDO65IVDCAR7W4AF3GI.json","view_paper":"https://pith.science/paper/OIAZHYZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.09082&json=true","fetch_graph":"https://pith.science/api/pith-number/OIAZHYZMDO65IVDCAR7W4AF3GI/graph.json","fetch_events":"https://pith.science/api/pith-number/OIAZHYZMDO65IVDCAR7W4AF3GI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIAZHYZMDO65IVDCAR7W4AF3GI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIAZHYZMDO65IVDCAR7W4AF3GI/action/storage_attestation","attest_author":"https://pith.science/pith/OIAZHYZMDO65IVDCAR7W4AF3GI/action/author_attestation","sign_citation":"https://pith.science/pith/OIAZHYZMDO65IVDCAR7W4AF3GI/action/citation_signature","submit_replication":"https://pith.science/pith/OIAZHYZMDO65IVDCAR7W4AF3GI/action/replication_record"}},"created_at":"2026-05-18T00:20:12.660008+00:00","updated_at":"2026-05-18T00:20:12.660008+00:00"}