{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CC3IYO5UGWJVQDTEL3AMKD3CMZ","short_pith_number":"pith:CC3IYO5U","schema_version":"1.0","canonical_sha256":"10b68c3bb43593580e645ec0c50f6266797d08dd1381ea8cec907c29150d77a3","source":{"kind":"arxiv","id":"2505.17150","version":1},"attestation_state":"computed","paper":{"title":"Efficient Training of Neural SDEs Using Stochastic Optimal Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.PR"],"primary_cat":"cs.LG","authors_text":"Guillaume Crevecoeur, Manfred Opper, Rembert Daems, Tolga Birdal","submitted_at":"2025-05-22T09:26:01Z","abstract_excerpt":"We present a hierarchical, control theory inspired method for variational inference (VI) for neural stochastic differential equations (SDEs). While VI for neural SDEs is a promising avenue for uncertainty-aware reasoning in time-series, it is computationally challenging due to the iterative nature of maximizing the ELBO. In this work, we propose to decompose the control term into linear and residual non-linear components and derive an optimal control term for linear SDEs, using stochastic optimal control. Modeling the non-linear component by a neural network, we show how to efficiently train n"},"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":"2505.17150","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T09:26:01Z","cross_cats_sorted":["cs.AI","math.PR"],"title_canon_sha256":"b533f44239a21dd564c9bac0fb2c5810afc238d1d6856738e0a4c393d3f7e2ff","abstract_canon_sha256":"1d1ebe6c657f0e17cfa4287c17e3537f2b77dc67313f2499c95eac0fc7b349b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:47.887811Z","signature_b64":"is7phjp+vo0Jxzmueis5xn16oNpTI/eDoP7u2oNHufldMZx7ANQJYy+TVDXieN53xTavK/W9R0tpvB4YN8e2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10b68c3bb43593580e645ec0c50f6266797d08dd1381ea8cec907c29150d77a3","last_reissued_at":"2026-07-05T11:07:47.887297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:47.887297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Training of Neural SDEs Using Stochastic Optimal Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.PR"],"primary_cat":"cs.LG","authors_text":"Guillaume Crevecoeur, Manfred Opper, Rembert Daems, Tolga Birdal","submitted_at":"2025-05-22T09:26:01Z","abstract_excerpt":"We present a hierarchical, control theory inspired method for variational inference (VI) for neural stochastic differential equations (SDEs). While VI for neural SDEs is a promising avenue for uncertainty-aware reasoning in time-series, it is computationally challenging due to the iterative nature of maximizing the ELBO. In this work, we propose to decompose the control term into linear and residual non-linear components and derive an optimal control term for linear SDEs, using stochastic optimal control. Modeling the non-linear component by a neural network, we show how to efficiently train n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17150","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/2505.17150/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":"2505.17150","created_at":"2026-07-05T11:07:47.887371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17150v1","created_at":"2026-07-05T11:07:47.887371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17150","created_at":"2026-07-05T11:07:47.887371+00:00"},{"alias_kind":"pith_short_12","alias_value":"CC3IYO5UGWJV","created_at":"2026-07-05T11:07:47.887371+00:00"},{"alias_kind":"pith_short_16","alias_value":"CC3IYO5UGWJVQDTE","created_at":"2026-07-05T11:07:47.887371+00:00"},{"alias_kind":"pith_short_8","alias_value":"CC3IYO5U","created_at":"2026-07-05T11:07:47.887371+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/CC3IYO5UGWJVQDTEL3AMKD3CMZ","json":"https://pith.science/pith/CC3IYO5UGWJVQDTEL3AMKD3CMZ.json","graph_json":"https://pith.science/api/pith-number/CC3IYO5UGWJVQDTEL3AMKD3CMZ/graph.json","events_json":"https://pith.science/api/pith-number/CC3IYO5UGWJVQDTEL3AMKD3CMZ/events.json","paper":"https://pith.science/paper/CC3IYO5U"},"agent_actions":{"view_html":"https://pith.science/pith/CC3IYO5UGWJVQDTEL3AMKD3CMZ","download_json":"https://pith.science/pith/CC3IYO5UGWJVQDTEL3AMKD3CMZ.json","view_paper":"https://pith.science/paper/CC3IYO5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17150&json=true","fetch_graph":"https://pith.science/api/pith-number/CC3IYO5UGWJVQDTEL3AMKD3CMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/CC3IYO5UGWJVQDTEL3AMKD3CMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CC3IYO5UGWJVQDTEL3AMKD3CMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CC3IYO5UGWJVQDTEL3AMKD3CMZ/action/storage_attestation","attest_author":"https://pith.science/pith/CC3IYO5UGWJVQDTEL3AMKD3CMZ/action/author_attestation","sign_citation":"https://pith.science/pith/CC3IYO5UGWJVQDTEL3AMKD3CMZ/action/citation_signature","submit_replication":"https://pith.science/pith/CC3IYO5UGWJVQDTEL3AMKD3CMZ/action/replication_record"}},"created_at":"2026-07-05T11:07:47.887371+00:00","updated_at":"2026-07-05T11:07:47.887371+00:00"}