{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Y2YZPP5RZIJVACKEPJOWNGVSRJ","short_pith_number":"pith:Y2YZPP5R","schema_version":"1.0","canonical_sha256":"c6b197bfb1ca135009447a5d669ab28a694eb3ee9d10830497bc2f914e3aa3b1","source":{"kind":"arxiv","id":"1803.01299","version":2},"attestation_state":"computed","paper":{"title":"An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qianxiao Li, Shuji Hao","submitted_at":"2018-03-04T04:37:49Z","abstract_excerpt":"Deep learning is formulated as a discrete-time optimal control problem. This allows one to characterize necessary conditions for optimality and develop training algorithms that do not rely on gradients with respect to the trainable parameters. In particular, we introduce the discrete-time method of successive approximations (MSA), which is based on the Pontryagin's maximum principle, for training neural networks. A rigorous error estimate for the discrete MSA is obtained, which sheds light on its dynamics and the means to stabilize the algorithm. The developed methods are applied to train, in "},"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":"1803.01299","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-04T04:37:49Z","cross_cats_sorted":[],"title_canon_sha256":"173c720be92a4ad460d5626e460a9d8b2978640aea5b5912e836440b3aaf30d5","abstract_canon_sha256":"1218f4b7a2a51007f1f1ae4c0ff124ab0a8f2355a196ebb68db8cb0ce77df4dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:21.674325Z","signature_b64":"L+dO/4cfnUJ/tj4gweDhw/E/KxuUAmYLZkSRNxWd+39sNmQmAvrbjWVRjrYA9rWEiKAJfimsSEQ81OtGJt1SBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6b197bfb1ca135009447a5d669ab28a694eb3ee9d10830497bc2f914e3aa3b1","last_reissued_at":"2026-05-18T00:14:21.673756Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:21.673756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qianxiao Li, Shuji Hao","submitted_at":"2018-03-04T04:37:49Z","abstract_excerpt":"Deep learning is formulated as a discrete-time optimal control problem. This allows one to characterize necessary conditions for optimality and develop training algorithms that do not rely on gradients with respect to the trainable parameters. In particular, we introduce the discrete-time method of successive approximations (MSA), which is based on the Pontryagin's maximum principle, for training neural networks. A rigorous error estimate for the discrete MSA is obtained, which sheds light on its dynamics and the means to stabilize the algorithm. The developed methods are applied to train, in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01299","kind":"arxiv","version":2},"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":"1803.01299","created_at":"2026-05-18T00:14:21.673832+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.01299v2","created_at":"2026-05-18T00:14:21.673832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01299","created_at":"2026-05-18T00:14:21.673832+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y2YZPP5RZIJV","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y2YZPP5RZIJVACKE","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y2YZPP5R","created_at":"2026-05-18T12:33:04.347982+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/Y2YZPP5RZIJVACKEPJOWNGVSRJ","json":"https://pith.science/pith/Y2YZPP5RZIJVACKEPJOWNGVSRJ.json","graph_json":"https://pith.science/api/pith-number/Y2YZPP5RZIJVACKEPJOWNGVSRJ/graph.json","events_json":"https://pith.science/api/pith-number/Y2YZPP5RZIJVACKEPJOWNGVSRJ/events.json","paper":"https://pith.science/paper/Y2YZPP5R"},"agent_actions":{"view_html":"https://pith.science/pith/Y2YZPP5RZIJVACKEPJOWNGVSRJ","download_json":"https://pith.science/pith/Y2YZPP5RZIJVACKEPJOWNGVSRJ.json","view_paper":"https://pith.science/paper/Y2YZPP5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.01299&json=true","fetch_graph":"https://pith.science/api/pith-number/Y2YZPP5RZIJVACKEPJOWNGVSRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Y2YZPP5RZIJVACKEPJOWNGVSRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y2YZPP5RZIJVACKEPJOWNGVSRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y2YZPP5RZIJVACKEPJOWNGVSRJ/action/storage_attestation","attest_author":"https://pith.science/pith/Y2YZPP5RZIJVACKEPJOWNGVSRJ/action/author_attestation","sign_citation":"https://pith.science/pith/Y2YZPP5RZIJVACKEPJOWNGVSRJ/action/citation_signature","submit_replication":"https://pith.science/pith/Y2YZPP5RZIJVACKEPJOWNGVSRJ/action/replication_record"}},"created_at":"2026-05-18T00:14:21.673832+00:00","updated_at":"2026-05-18T00:14:21.673832+00:00"}