{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QF4XF2UDJT46XDY4RYXF6ZWNDH","short_pith_number":"pith:QF4XF2UD","schema_version":"1.0","canonical_sha256":"817972ea834cf9eb8f1c8e2e5f66cd19efbc050e367352accadb868a5ad731ca","source":{"kind":"arxiv","id":"2110.06897","version":2},"attestation_state":"computed","paper":{"title":"Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.ST","physics.comp-ph","stat.ML","stat.TH"],"primary_cat":"math.NA","authors_text":"Haoxuan Chen, Jianfeng Lu, Jose Blanchet, Lexing Ying, Yiping Lu","submitted_at":"2021-10-13T17:26:31Z","abstract_excerpt":"In this paper, we study the statistical limits of deep learning techniques for solving elliptic partial differential equations (PDEs) from random samples using the Deep Ritz Method (DRM) and Physics-Informed Neural Networks (PINNs). To simplify the problem, we focus on a prototype elliptic PDE: the Schr\\\"odinger equation on a hypercube with zero Dirichlet boundary condition, which has wide application in the quantum-mechanical systems. We establish upper and lower bounds for both methods, which improves upon concurrently developed upper bounds for this problem via a fast rate generalization bo"},"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":"2110.06897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2021-10-13T17:26:31Z","cross_cats_sorted":["cs.LG","cs.NA","math.ST","physics.comp-ph","stat.ML","stat.TH"],"title_canon_sha256":"84f8690cc062f40414c643575a847bdbd65fc467491bdafdd7342cbf7fba7996","abstract_canon_sha256":"b2741f41fd8dc047f31f24b53172ba5af816f709d25778351fa0758e8c684cf2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:31.368830Z","signature_b64":"/irHoIjuvFXBUYlqj4nQAKUAkYeXKdEj1ker4+5aguyWl90tJr5s91CkGT9oMCg5xCuULADJ3R6ZP0xJNGPrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"817972ea834cf9eb8f1c8e2e5f66cd19efbc050e367352accadb868a5ad731ca","last_reissued_at":"2026-07-05T03:31:31.368339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:31.368339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.ST","physics.comp-ph","stat.ML","stat.TH"],"primary_cat":"math.NA","authors_text":"Haoxuan Chen, Jianfeng Lu, Jose Blanchet, Lexing Ying, Yiping Lu","submitted_at":"2021-10-13T17:26:31Z","abstract_excerpt":"In this paper, we study the statistical limits of deep learning techniques for solving elliptic partial differential equations (PDEs) from random samples using the Deep Ritz Method (DRM) and Physics-Informed Neural Networks (PINNs). To simplify the problem, we focus on a prototype elliptic PDE: the Schr\\\"odinger equation on a hypercube with zero Dirichlet boundary condition, which has wide application in the quantum-mechanical systems. We establish upper and lower bounds for both methods, which improves upon concurrently developed upper bounds for this problem via a fast rate generalization bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06897","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/2110.06897/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":"2110.06897","created_at":"2026-07-05T03:31:31.368401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.06897v2","created_at":"2026-07-05T03:31:31.368401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06897","created_at":"2026-07-05T03:31:31.368401+00:00"},{"alias_kind":"pith_short_12","alias_value":"QF4XF2UDJT46","created_at":"2026-07-05T03:31:31.368401+00:00"},{"alias_kind":"pith_short_16","alias_value":"QF4XF2UDJT46XDY4","created_at":"2026-07-05T03:31:31.368401+00:00"},{"alias_kind":"pith_short_8","alias_value":"QF4XF2UD","created_at":"2026-07-05T03:31:31.368401+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06369","citing_title":"Feature Learning for the High Dimensional Stationary Sch\\\"odinger Equation with Deep Ritz Method","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16733","citing_title":"Concentration Inequalities for Sample Cross-Covariances","ref_index":295,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08672","citing_title":"Posterior Concentration of Bayesian Physics-Informed Neural Networks for Elliptic PDEs","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QF4XF2UDJT46XDY4RYXF6ZWNDH","json":"https://pith.science/pith/QF4XF2UDJT46XDY4RYXF6ZWNDH.json","graph_json":"https://pith.science/api/pith-number/QF4XF2UDJT46XDY4RYXF6ZWNDH/graph.json","events_json":"https://pith.science/api/pith-number/QF4XF2UDJT46XDY4RYXF6ZWNDH/events.json","paper":"https://pith.science/paper/QF4XF2UD"},"agent_actions":{"view_html":"https://pith.science/pith/QF4XF2UDJT46XDY4RYXF6ZWNDH","download_json":"https://pith.science/pith/QF4XF2UDJT46XDY4RYXF6ZWNDH.json","view_paper":"https://pith.science/paper/QF4XF2UD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.06897&json=true","fetch_graph":"https://pith.science/api/pith-number/QF4XF2UDJT46XDY4RYXF6ZWNDH/graph.json","fetch_events":"https://pith.science/api/pith-number/QF4XF2UDJT46XDY4RYXF6ZWNDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QF4XF2UDJT46XDY4RYXF6ZWNDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QF4XF2UDJT46XDY4RYXF6ZWNDH/action/storage_attestation","attest_author":"https://pith.science/pith/QF4XF2UDJT46XDY4RYXF6ZWNDH/action/author_attestation","sign_citation":"https://pith.science/pith/QF4XF2UDJT46XDY4RYXF6ZWNDH/action/citation_signature","submit_replication":"https://pith.science/pith/QF4XF2UDJT46XDY4RYXF6ZWNDH/action/replication_record"}},"created_at":"2026-07-05T03:31:31.368401+00:00","updated_at":"2026-07-05T03:31:31.368401+00:00"}