{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OBPAED322B7CC2UE6YVKEHKBG2","short_pith_number":"pith:OBPAED32","schema_version":"1.0","canonical_sha256":"705e020f7ad07e216a84f62aa21d4136a2002df4a2d36de8ecb990849b05643a","source":{"kind":"arxiv","id":"2405.11451","version":1},"attestation_state":"computed","paper":{"title":"Error Analysis of Three-Layer Neural Network Trained with PGD for Deep Ritz Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.AP","stat.ML"],"primary_cat":"math.NA","authors_text":"Yang Wang, Yanming Lai, Yuling Jiao","submitted_at":"2024-05-19T05:07:09Z","abstract_excerpt":"Machine learning is a rapidly advancing field with diverse applications across various domains. One prominent area of research is the utilization of deep learning techniques for solving partial differential equations(PDEs). In this work, we specifically focus on employing a three-layer tanh neural network within the framework of the deep Ritz method(DRM) to solve second-order elliptic equations with three different types of boundary conditions. We perform projected gradient descent(PDG) to train the three-layer network and we establish its global convergence. To the best of our knowledge, we a"},"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":"2405.11451","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2024-05-19T05:07:09Z","cross_cats_sorted":["cs.AI","cs.NA","math.AP","stat.ML"],"title_canon_sha256":"1eb6aafe8f68d1ef962891be929b11e72e377c77684610fa4c30dd5ba92d5a66","abstract_canon_sha256":"c31a35efefddf7c55b2139926b46f336c90444509c61dc349e9b2ea411d2e456"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:39.610819Z","signature_b64":"PstTmK1XfYBcNabRbXzhOkurFqaubYW/Yj758JVBjTdvfV2uTgSOW1bEAcgePfivU7xCXjCeNZQhkpO+5AOUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"705e020f7ad07e216a84f62aa21d4136a2002df4a2d36de8ecb990849b05643a","last_reissued_at":"2026-07-05T08:20:39.606960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:39.606960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Error Analysis of Three-Layer Neural Network Trained with PGD for Deep Ritz Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.AP","stat.ML"],"primary_cat":"math.NA","authors_text":"Yang Wang, Yanming Lai, Yuling Jiao","submitted_at":"2024-05-19T05:07:09Z","abstract_excerpt":"Machine learning is a rapidly advancing field with diverse applications across various domains. One prominent area of research is the utilization of deep learning techniques for solving partial differential equations(PDEs). In this work, we specifically focus on employing a three-layer tanh neural network within the framework of the deep Ritz method(DRM) to solve second-order elliptic equations with three different types of boundary conditions. We perform projected gradient descent(PDG) to train the three-layer network and we establish its global convergence. To the best of our knowledge, we a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11451","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/2405.11451/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":"2405.11451","created_at":"2026-07-05T08:20:39.607013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11451v1","created_at":"2026-07-05T08:20:39.607013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11451","created_at":"2026-07-05T08:20:39.607013+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBPAED322B7C","created_at":"2026-07-05T08:20:39.607013+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBPAED322B7CC2UE","created_at":"2026-07-05T08:20:39.607013+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBPAED32","created_at":"2026-07-05T08:20:39.607013+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/OBPAED322B7CC2UE6YVKEHKBG2","json":"https://pith.science/pith/OBPAED322B7CC2UE6YVKEHKBG2.json","graph_json":"https://pith.science/api/pith-number/OBPAED322B7CC2UE6YVKEHKBG2/graph.json","events_json":"https://pith.science/api/pith-number/OBPAED322B7CC2UE6YVKEHKBG2/events.json","paper":"https://pith.science/paper/OBPAED32"},"agent_actions":{"view_html":"https://pith.science/pith/OBPAED322B7CC2UE6YVKEHKBG2","download_json":"https://pith.science/pith/OBPAED322B7CC2UE6YVKEHKBG2.json","view_paper":"https://pith.science/paper/OBPAED32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11451&json=true","fetch_graph":"https://pith.science/api/pith-number/OBPAED322B7CC2UE6YVKEHKBG2/graph.json","fetch_events":"https://pith.science/api/pith-number/OBPAED322B7CC2UE6YVKEHKBG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBPAED322B7CC2UE6YVKEHKBG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBPAED322B7CC2UE6YVKEHKBG2/action/storage_attestation","attest_author":"https://pith.science/pith/OBPAED322B7CC2UE6YVKEHKBG2/action/author_attestation","sign_citation":"https://pith.science/pith/OBPAED322B7CC2UE6YVKEHKBG2/action/citation_signature","submit_replication":"https://pith.science/pith/OBPAED322B7CC2UE6YVKEHKBG2/action/replication_record"}},"created_at":"2026-07-05T08:20:39.607013+00:00","updated_at":"2026-07-05T08:20:39.607013+00:00"}