{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CMG273SLR4OP3DS2CWQJERH5XA","short_pith_number":"pith:CMG273SL","schema_version":"1.0","canonical_sha256":"130dafee4b8f1cfd8e5a15a09244fdb82fae85dade7f85daee204a4c93f85856","source":{"kind":"arxiv","id":"2502.15642","version":1},"attestation_state":"computed","paper":{"title":"Training Neural ODEs Using Fully Discretized Simultaneous Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Calvin Tsay, Mariia Shapovalova","submitted_at":"2025-02-21T18:10:26Z","abstract_excerpt":"Neural Ordinary Differential Equations (Neural ODEs) represent continuous-time dynamics with neural networks, offering advancements for modeling and control tasks. However, training Neural ODEs requires solving differential equations at each epoch, leading to high computational costs. This work investigates simultaneous optimization methods as a faster training alternative. In particular, we employ a collocation-based, fully discretized formulation and use IPOPT--a solver for large-scale nonlinear optimization--to simultaneously optimize collocation coefficients and neural network parameters. "},"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":"2502.15642","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T18:10:26Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"e4e0bf2c8675ac7119185cfb820af4e76c3236d7f64cb13326615630a7bc2dde","abstract_canon_sha256":"c915aa377bea9b00d3d7ac7a21622040358123da1915a4fed24be82a7ff59bdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:04.990835Z","signature_b64":"/rrie7hsXED7Xhh3HSBGHMlTuVtXuuyTo38Y2yyWs0CJfZw3YyD1X0a46spDwtxFQDiPAYtr9g11GKGyfy8yCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"130dafee4b8f1cfd8e5a15a09244fdb82fae85dade7f85daee204a4c93f85856","last_reissued_at":"2026-07-05T10:18:04.990430Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:04.990430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Neural ODEs Using Fully Discretized Simultaneous Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Calvin Tsay, Mariia Shapovalova","submitted_at":"2025-02-21T18:10:26Z","abstract_excerpt":"Neural Ordinary Differential Equations (Neural ODEs) represent continuous-time dynamics with neural networks, offering advancements for modeling and control tasks. However, training Neural ODEs requires solving differential equations at each epoch, leading to high computational costs. This work investigates simultaneous optimization methods as a faster training alternative. In particular, we employ a collocation-based, fully discretized formulation and use IPOPT--a solver for large-scale nonlinear optimization--to simultaneously optimize collocation coefficients and neural network parameters. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15642","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.15642/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2502.15642","created_at":"2026-07-05T10:18:04.990483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15642v1","created_at":"2026-07-05T10:18:04.990483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15642","created_at":"2026-07-05T10:18:04.990483+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMG273SLR4OP","created_at":"2026-07-05T10:18:04.990483+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMG273SLR4OP3DS2","created_at":"2026-07-05T10:18:04.990483+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMG273SL","created_at":"2026-07-05T10:18:04.990483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.03552","citing_title":"Efficient Training of Physics-enhanced Neural ODEs via Direct Collocation and Nonlinear Programming","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMG273SLR4OP3DS2CWQJERH5XA","json":"https://pith.science/pith/CMG273SLR4OP3DS2CWQJERH5XA.json","graph_json":"https://pith.science/api/pith-number/CMG273SLR4OP3DS2CWQJERH5XA/graph.json","events_json":"https://pith.science/api/pith-number/CMG273SLR4OP3DS2CWQJERH5XA/events.json","paper":"https://pith.science/paper/CMG273SL"},"agent_actions":{"view_html":"https://pith.science/pith/CMG273SLR4OP3DS2CWQJERH5XA","download_json":"https://pith.science/pith/CMG273SLR4OP3DS2CWQJERH5XA.json","view_paper":"https://pith.science/paper/CMG273SL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15642&json=true","fetch_graph":"https://pith.science/api/pith-number/CMG273SLR4OP3DS2CWQJERH5XA/graph.json","fetch_events":"https://pith.science/api/pith-number/CMG273SLR4OP3DS2CWQJERH5XA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMG273SLR4OP3DS2CWQJERH5XA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMG273SLR4OP3DS2CWQJERH5XA/action/storage_attestation","attest_author":"https://pith.science/pith/CMG273SLR4OP3DS2CWQJERH5XA/action/author_attestation","sign_citation":"https://pith.science/pith/CMG273SLR4OP3DS2CWQJERH5XA/action/citation_signature","submit_replication":"https://pith.science/pith/CMG273SLR4OP3DS2CWQJERH5XA/action/replication_record"}},"created_at":"2026-07-05T10:18:04.990483+00:00","updated_at":"2026-07-05T10:18:04.990483+00:00"}