{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WWZRHSLCYFCZD3W2T4FCAXUHEF","short_pith_number":"pith:WWZRHSLC","schema_version":"1.0","canonical_sha256":"b5b313c962c14591eeda9f0a205e87217fc944984a84db5303d863d06e9ac349","source":{"kind":"arxiv","id":"2103.13330","version":2},"attestation_state":"computed","paper":{"title":"Convergence Rate Analysis for Deep Ritz Method","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Chenguang Duan, Xiliang Lu, Yanming Lai, Yuling Jiao, Zhijian Yang","submitted_at":"2021-03-24T16:30:23Z","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{wan11} for second order elliptic equations with Neumann boundary conditions. We establish the first nonasymptotic convergence rate in $H^1$ norm for DRM using deep networks with $\\mathrm{ReLU}^2$ activation functions. In addition to providing a theoretical justification of DRM, our study also shed light on how to set the hyper-parameter"},"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":"2103.13330","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2021-03-24T16:30:23Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"73a8ec9f9e4fcaf0b10084129d3872746dd28cff11e4b94d7f2fe71b4357da03","abstract_canon_sha256":"7ee3982a3e69350ee03597a49995a0ec2fdfd1c7f6700fe3c0a6c4ef36368c8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:22.694639Z","signature_b64":"XwXp+8OBAfnfUA2OREckU8uoDcBfwau69IakM9sy2URlJgMaTAeuYqM7y/YvsUPg2rgg4rCMBpf5gc25sM96DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5b313c962c14591eeda9f0a205e87217fc944984a84db5303d863d06e9ac349","last_reissued_at":"2026-07-05T04:13:22.694065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:22.694065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence Rate Analysis for Deep Ritz Method","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Chenguang Duan, Xiliang Lu, Yanming Lai, Yuling Jiao, Zhijian Yang","submitted_at":"2021-03-24T16:30:23Z","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{wan11} for second order elliptic equations with Neumann boundary conditions. We establish the first nonasymptotic convergence rate in $H^1$ norm for DRM using deep networks with $\\mathrm{ReLU}^2$ activation functions. In addition to providing a theoretical justification of DRM, our study also shed light on how to set the hyper-parameter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13330","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/2103.13330/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":"2103.13330","created_at":"2026-07-05T04:13:22.694140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.13330v2","created_at":"2026-07-05T04:13:22.694140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13330","created_at":"2026-07-05T04:13:22.694140+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWZRHSLCYFCZ","created_at":"2026-07-05T04:13:22.694140+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWZRHSLCYFCZD3W2","created_at":"2026-07-05T04:13:22.694140+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWZRHSLC","created_at":"2026-07-05T04:13:22.694140+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/WWZRHSLCYFCZD3W2T4FCAXUHEF","json":"https://pith.science/pith/WWZRHSLCYFCZD3W2T4FCAXUHEF.json","graph_json":"https://pith.science/api/pith-number/WWZRHSLCYFCZD3W2T4FCAXUHEF/graph.json","events_json":"https://pith.science/api/pith-number/WWZRHSLCYFCZD3W2T4FCAXUHEF/events.json","paper":"https://pith.science/paper/WWZRHSLC"},"agent_actions":{"view_html":"https://pith.science/pith/WWZRHSLCYFCZD3W2T4FCAXUHEF","download_json":"https://pith.science/pith/WWZRHSLCYFCZD3W2T4FCAXUHEF.json","view_paper":"https://pith.science/paper/WWZRHSLC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.13330&json=true","fetch_graph":"https://pith.science/api/pith-number/WWZRHSLCYFCZD3W2T4FCAXUHEF/graph.json","fetch_events":"https://pith.science/api/pith-number/WWZRHSLCYFCZD3W2T4FCAXUHEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWZRHSLCYFCZD3W2T4FCAXUHEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWZRHSLCYFCZD3W2T4FCAXUHEF/action/storage_attestation","attest_author":"https://pith.science/pith/WWZRHSLCYFCZD3W2T4FCAXUHEF/action/author_attestation","sign_citation":"https://pith.science/pith/WWZRHSLCYFCZD3W2T4FCAXUHEF/action/citation_signature","submit_replication":"https://pith.science/pith/WWZRHSLCYFCZD3W2T4FCAXUHEF/action/replication_record"}},"created_at":"2026-07-05T04:13:22.694140+00:00","updated_at":"2026-07-05T04:13:22.694140+00:00"}