{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DLS42QIFGCCSXUPJY73HRY5YFK","short_pith_number":"pith:DLS42QIF","schema_version":"1.0","canonical_sha256":"1ae5cd410530852bd1e9c7f678e3b82a9f99d1db128952c298278ed7ae8e605c","source":{"kind":"arxiv","id":"2306.17648","version":2},"attestation_state":"computed","paper":{"title":"Enhancing training of physics-informed neural networks using domain-decomposition based preconditioning strategies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.OC"],"primary_cat":"math.NA","authors_text":"Alena Kopani\\v{c}\\'akov\\'a, George Em Karniadakis, Hardik Kothari, Rolf Krause","submitted_at":"2023-06-30T13:35:09Z","abstract_excerpt":"We propose to enhance the training of physics-informed neural networks (PINNs). To this aim, we introduce nonlinear additive and multiplicative preconditioning strategies for the widely used L-BFGS optimizer. The nonlinear preconditioners are constructed by utilizing the Schwarz domain-decomposition framework, where the parameters of the network are decomposed in a layer-wise manner. Through a series of numerical experiments, we demonstrate that both, additive and multiplicative preconditioners significantly improve the convergence of the standard L-BFGS optimizer, while providing more accurat"},"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":"2306.17648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.NA","submitted_at":"2023-06-30T13:35:09Z","cross_cats_sorted":["cs.LG","cs.NA","math.OC"],"title_canon_sha256":"b2cb3b3fe819e3a83e81d5ff5aca73e5dd67813632077f1c1cf7bc4a519353f8","abstract_canon_sha256":"fad53a1771fe923531b2e38a0c474082344625b1621537ecf0e4eb52a6977dd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:28.207265Z","signature_b64":"+lyhx8AgLMGshVsMBOvi8L1VV4wB1Jkdaq/8RDSrR8p0fZDB2jij7h8tigkvfOa+7TgciviXuWxmSS5w3E+ADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ae5cd410530852bd1e9c7f678e3b82a9f99d1db128952c298278ed7ae8e605c","last_reissued_at":"2026-07-05T08:07:28.206814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:28.206814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing training of physics-informed neural networks using domain-decomposition based preconditioning strategies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.OC"],"primary_cat":"math.NA","authors_text":"Alena Kopani\\v{c}\\'akov\\'a, George Em Karniadakis, Hardik Kothari, Rolf Krause","submitted_at":"2023-06-30T13:35:09Z","abstract_excerpt":"We propose to enhance the training of physics-informed neural networks (PINNs). To this aim, we introduce nonlinear additive and multiplicative preconditioning strategies for the widely used L-BFGS optimizer. The nonlinear preconditioners are constructed by utilizing the Schwarz domain-decomposition framework, where the parameters of the network are decomposed in a layer-wise manner. Through a series of numerical experiments, we demonstrate that both, additive and multiplicative preconditioners significantly improve the convergence of the standard L-BFGS optimizer, while providing more accurat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17648","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.17648/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":"2306.17648","created_at":"2026-07-05T08:07:28.206866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.17648v2","created_at":"2026-07-05T08:07:28.206866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17648","created_at":"2026-07-05T08:07:28.206866+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLS42QIFGCCS","created_at":"2026-07-05T08:07:28.206866+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLS42QIFGCCSXUPJ","created_at":"2026-07-05T08:07:28.206866+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLS42QIF","created_at":"2026-07-05T08:07:28.206866+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/DLS42QIFGCCSXUPJY73HRY5YFK","json":"https://pith.science/pith/DLS42QIFGCCSXUPJY73HRY5YFK.json","graph_json":"https://pith.science/api/pith-number/DLS42QIFGCCSXUPJY73HRY5YFK/graph.json","events_json":"https://pith.science/api/pith-number/DLS42QIFGCCSXUPJY73HRY5YFK/events.json","paper":"https://pith.science/paper/DLS42QIF"},"agent_actions":{"view_html":"https://pith.science/pith/DLS42QIFGCCSXUPJY73HRY5YFK","download_json":"https://pith.science/pith/DLS42QIFGCCSXUPJY73HRY5YFK.json","view_paper":"https://pith.science/paper/DLS42QIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.17648&json=true","fetch_graph":"https://pith.science/api/pith-number/DLS42QIFGCCSXUPJY73HRY5YFK/graph.json","fetch_events":"https://pith.science/api/pith-number/DLS42QIFGCCSXUPJY73HRY5YFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLS42QIFGCCSXUPJY73HRY5YFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLS42QIFGCCSXUPJY73HRY5YFK/action/storage_attestation","attest_author":"https://pith.science/pith/DLS42QIFGCCSXUPJY73HRY5YFK/action/author_attestation","sign_citation":"https://pith.science/pith/DLS42QIFGCCSXUPJY73HRY5YFK/action/citation_signature","submit_replication":"https://pith.science/pith/DLS42QIFGCCSXUPJY73HRY5YFK/action/replication_record"}},"created_at":"2026-07-05T08:07:28.206866+00:00","updated_at":"2026-07-05T08:07:28.206866+00:00"}