{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B45HDIW4IJVEJW45BYRPRI5TEB","short_pith_number":"pith:B45HDIW4","schema_version":"1.0","canonical_sha256":"0f3a71a2dc426a44db9d0e22f8a3b320612c4ce24e6d4bcca51db3232ef93482","source":{"kind":"arxiv","id":"2107.14478","version":2},"attestation_state":"computed","paper":{"title":"Error Analysis of Deep Ritz Methods for Elliptic Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Yang Wang, Yanming Lai, Yisu Lo, Yuling Jiao, Yunfei Yang","submitted_at":"2021-07-30T08:02:05Z","abstract_excerpt":"Using deep neural networks to solve PDEs has attracted a lot of attentions recently. However, why the deep learning method works is falling far behind its empirical success. In this paper, we provide a rigorous numerical analysis on deep Ritz method (DRM) \\cite{Weinan2017The} for second order elliptic equations with Drichilet, Neumann and Robin boundary condition, respectively. We establish the first nonasymptotic convergence rate in $H^1$ norm for DRM using deep networks with smooth activation functions including logistic and hyperbolic tangent functions. Our results show how to set the hyper"},"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":"2107.14478","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2021-07-30T08:02:05Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"1992575bd9ca9fe7a7826af19d96f0ade86e982925f5ee685d3d2c6f851fd9cb","abstract_canon_sha256":"421938bfd516452581a93a909f9fdcfb8ea0ffa980c6357ad008e61cdb6e395d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:31.892108Z","signature_b64":"xshKPikhZXzZWdeFbjAi8pWNgxY5aBYl2ew0IeOb3S/E1MmbeVt0DOQ7pUXdhELPGFMh2HQjpWZWkSkiakBMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f3a71a2dc426a44db9d0e22f8a3b320612c4ce24e6d4bcca51db3232ef93482","last_reissued_at":"2026-07-05T03:11:31.891715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:31.891715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Error Analysis of Deep Ritz Methods for Elliptic Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Yang Wang, Yanming Lai, Yisu Lo, Yuling Jiao, Yunfei Yang","submitted_at":"2021-07-30T08:02:05Z","abstract_excerpt":"Using deep neural networks to solve PDEs has attracted a lot of attentions recently. However, why the deep learning method works is falling far behind its empirical success. In this paper, we provide a rigorous numerical analysis on deep Ritz method (DRM) \\cite{Weinan2017The} for second order elliptic equations with Drichilet, Neumann and Robin boundary condition, respectively. We establish the first nonasymptotic convergence rate in $H^1$ norm for DRM using deep networks with smooth activation functions including logistic and hyperbolic tangent functions. Our results show how to set the hyper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.14478","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/2107.14478/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":"2107.14478","created_at":"2026-07-05T03:11:31.891773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.14478v2","created_at":"2026-07-05T03:11:31.891773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.14478","created_at":"2026-07-05T03:11:31.891773+00:00"},{"alias_kind":"pith_short_12","alias_value":"B45HDIW4IJVE","created_at":"2026-07-05T03:11:31.891773+00:00"},{"alias_kind":"pith_short_16","alias_value":"B45HDIW4IJVEJW45","created_at":"2026-07-05T03:11:31.891773+00:00"},{"alias_kind":"pith_short_8","alias_value":"B45HDIW4","created_at":"2026-07-05T03:11:31.891773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11222","citing_title":"An Imbalanced Learning-based Sampling Method for Physics-informed Neural Networks","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B45HDIW4IJVEJW45BYRPRI5TEB","json":"https://pith.science/pith/B45HDIW4IJVEJW45BYRPRI5TEB.json","graph_json":"https://pith.science/api/pith-number/B45HDIW4IJVEJW45BYRPRI5TEB/graph.json","events_json":"https://pith.science/api/pith-number/B45HDIW4IJVEJW45BYRPRI5TEB/events.json","paper":"https://pith.science/paper/B45HDIW4"},"agent_actions":{"view_html":"https://pith.science/pith/B45HDIW4IJVEJW45BYRPRI5TEB","download_json":"https://pith.science/pith/B45HDIW4IJVEJW45BYRPRI5TEB.json","view_paper":"https://pith.science/paper/B45HDIW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.14478&json=true","fetch_graph":"https://pith.science/api/pith-number/B45HDIW4IJVEJW45BYRPRI5TEB/graph.json","fetch_events":"https://pith.science/api/pith-number/B45HDIW4IJVEJW45BYRPRI5TEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B45HDIW4IJVEJW45BYRPRI5TEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B45HDIW4IJVEJW45BYRPRI5TEB/action/storage_attestation","attest_author":"https://pith.science/pith/B45HDIW4IJVEJW45BYRPRI5TEB/action/author_attestation","sign_citation":"https://pith.science/pith/B45HDIW4IJVEJW45BYRPRI5TEB/action/citation_signature","submit_replication":"https://pith.science/pith/B45HDIW4IJVEJW45BYRPRI5TEB/action/replication_record"}},"created_at":"2026-07-05T03:11:31.891773+00:00","updated_at":"2026-07-05T03:11:31.891773+00:00"}