{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QJS7WMCWDFTBXOERZBZHPSRHBP","short_pith_number":"pith:QJS7WMCW","schema_version":"1.0","canonical_sha256":"8265fb305619661bb891c87277ca270bc0a500cdcfe9044932da2d50703862eb","source":{"kind":"arxiv","id":"2305.06000","version":1},"attestation_state":"computed","paper":{"title":"Global Convergence of Deep Galerkin and PINNs Methods for Solving Partial Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Deqing Jiang, Justin Sirignano, Samuel N. Cohen","submitted_at":"2023-05-10T09:20:11Z","abstract_excerpt":"Numerically solving high-dimensional partial differential equations (PDEs) is a major challenge. Conventional methods, such as finite difference methods, are unable to solve high-dimensional PDEs due to the curse-of-dimensionality. A variety of deep learning methods have been recently developed to try and solve high-dimensional PDEs by approximating the solution using a neural network. In this paper, we prove global convergence for one of the commonly-used deep learning algorithms for solving PDEs, the Deep Galerkin Method (DGM). DGM trains a neural network approximator to solve the PDE using "},"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":"2305.06000","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2023-05-10T09:20:11Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"d3dc8de17e742527e7defe21c1cf8dc4e73ee803a0e6c924a0704814cf2743e6","abstract_canon_sha256":"169e7b332a120f539a2cdf54d59dfec2cf03c74a87833a9bdf8163894093768c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:58.597483Z","signature_b64":"XWCttMoLvWqOZpWLmhKiOq8Q4zQON6nW4+BokVqqZKu+jB1dWV7fA9AtHT+TOWudvvvi9oDayE2xeolp3shgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8265fb305619661bb891c87277ca270bc0a500cdcfe9044932da2d50703862eb","last_reissued_at":"2026-07-05T06:08:58.597122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:58.597122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global Convergence of Deep Galerkin and PINNs Methods for Solving Partial Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Deqing Jiang, Justin Sirignano, Samuel N. Cohen","submitted_at":"2023-05-10T09:20:11Z","abstract_excerpt":"Numerically solving high-dimensional partial differential equations (PDEs) is a major challenge. Conventional methods, such as finite difference methods, are unable to solve high-dimensional PDEs due to the curse-of-dimensionality. A variety of deep learning methods have been recently developed to try and solve high-dimensional PDEs by approximating the solution using a neural network. In this paper, we prove global convergence for one of the commonly-used deep learning algorithms for solving PDEs, the Deep Galerkin Method (DGM). DGM trains a neural network approximator to solve the PDE using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06000","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/2305.06000/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":"2305.06000","created_at":"2026-07-05T06:08:58.597179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.06000v1","created_at":"2026-07-05T06:08:58.597179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06000","created_at":"2026-07-05T06:08:58.597179+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJS7WMCWDFTB","created_at":"2026-07-05T06:08:58.597179+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJS7WMCWDFTBXOER","created_at":"2026-07-05T06:08:58.597179+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJS7WMCW","created_at":"2026-07-05T06:08:58.597179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.06428","citing_title":"Neural Actor-Critic Methods for Hamilton-Jacobi-Bellman PDEs: Asymptotic Analysis and Numerical Studies","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27052","citing_title":"Man, Machine, and Mathematics","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QJS7WMCWDFTBXOERZBZHPSRHBP","json":"https://pith.science/pith/QJS7WMCWDFTBXOERZBZHPSRHBP.json","graph_json":"https://pith.science/api/pith-number/QJS7WMCWDFTBXOERZBZHPSRHBP/graph.json","events_json":"https://pith.science/api/pith-number/QJS7WMCWDFTBXOERZBZHPSRHBP/events.json","paper":"https://pith.science/paper/QJS7WMCW"},"agent_actions":{"view_html":"https://pith.science/pith/QJS7WMCWDFTBXOERZBZHPSRHBP","download_json":"https://pith.science/pith/QJS7WMCWDFTBXOERZBZHPSRHBP.json","view_paper":"https://pith.science/paper/QJS7WMCW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.06000&json=true","fetch_graph":"https://pith.science/api/pith-number/QJS7WMCWDFTBXOERZBZHPSRHBP/graph.json","fetch_events":"https://pith.science/api/pith-number/QJS7WMCWDFTBXOERZBZHPSRHBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJS7WMCWDFTBXOERZBZHPSRHBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJS7WMCWDFTBXOERZBZHPSRHBP/action/storage_attestation","attest_author":"https://pith.science/pith/QJS7WMCWDFTBXOERZBZHPSRHBP/action/author_attestation","sign_citation":"https://pith.science/pith/QJS7WMCWDFTBXOERZBZHPSRHBP/action/citation_signature","submit_replication":"https://pith.science/pith/QJS7WMCWDFTBXOERZBZHPSRHBP/action/replication_record"}},"created_at":"2026-07-05T06:08:58.597179+00:00","updated_at":"2026-07-05T06:08:58.597179+00:00"}