{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HDKTOLJIOE7IEQ4JTS47ACJNPW","short_pith_number":"pith:HDKTOLJI","schema_version":"1.0","canonical_sha256":"38d5372d28713e8243899cb9f0092d7d91ce21a6745dcced2625fa43b9fa2626","source":{"kind":"arxiv","id":"2407.02827","version":3},"attestation_state":"computed","paper":{"title":"Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Bin Shan, Ting Du, Wang Kong, Xianliang Xu, Ye Li, Zhongyi Huang","submitted_at":"2024-07-03T06:10:41Z","abstract_excerpt":"The optimization algorithms are crucial in training physics-informed neural networks (PINNs), as unsuitable methods may lead to poor solutions. Compared to the common gradient descent (GD) algorithm, implicit gradient descent (IGD) outperforms it in handling certain multi-scale problems. In this paper, we provide convergence analysis for the IGD in training over-parameterized two-layer PINNs. We first derive the training dynamics of IGD in training two-layer PINNs. Then, over-parameterization allows us to prove that the randomly initialized IGD converges to a globally optimal solution at a lin"},"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":"2407.02827","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T06:10:41Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"efc64b0ca261b35cbd1d26d30961a45057942c324e7a2f901837d26202f61ec1","abstract_canon_sha256":"88afc297cfb89855074cc809bc5bba5ea9bb199280ae80cd53fca45404b93fcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:35.017934Z","signature_b64":"eonnk4dpt+LIZuWUBRQVdyLFV8bs7If2fj2Ag4JAJkZvEGCkmzyNPPVVSBB8vQoTG31pIqNIy1/S7bO8azyBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38d5372d28713e8243899cb9f0092d7d91ce21a6745dcced2625fa43b9fa2626","last_reissued_at":"2026-07-05T11:46:35.017364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:35.017364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Bin Shan, Ting Du, Wang Kong, Xianliang Xu, Ye Li, Zhongyi Huang","submitted_at":"2024-07-03T06:10:41Z","abstract_excerpt":"The optimization algorithms are crucial in training physics-informed neural networks (PINNs), as unsuitable methods may lead to poor solutions. Compared to the common gradient descent (GD) algorithm, implicit gradient descent (IGD) outperforms it in handling certain multi-scale problems. In this paper, we provide convergence analysis for the IGD in training over-parameterized two-layer PINNs. We first derive the training dynamics of IGD in training two-layer PINNs. Then, over-parameterization allows us to prove that the randomly initialized IGD converges to a globally optimal solution at a lin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02827","kind":"arxiv","version":3},"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/2407.02827/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":"2407.02827","created_at":"2026-07-05T11:46:35.017429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02827v3","created_at":"2026-07-05T11:46:35.017429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02827","created_at":"2026-07-05T11:46:35.017429+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDKTOLJIOE7I","created_at":"2026-07-05T11:46:35.017429+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDKTOLJIOE7IEQ4J","created_at":"2026-07-05T11:46:35.017429+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDKTOLJI","created_at":"2026-07-05T11:46:35.017429+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/HDKTOLJIOE7IEQ4JTS47ACJNPW","json":"https://pith.science/pith/HDKTOLJIOE7IEQ4JTS47ACJNPW.json","graph_json":"https://pith.science/api/pith-number/HDKTOLJIOE7IEQ4JTS47ACJNPW/graph.json","events_json":"https://pith.science/api/pith-number/HDKTOLJIOE7IEQ4JTS47ACJNPW/events.json","paper":"https://pith.science/paper/HDKTOLJI"},"agent_actions":{"view_html":"https://pith.science/pith/HDKTOLJIOE7IEQ4JTS47ACJNPW","download_json":"https://pith.science/pith/HDKTOLJIOE7IEQ4JTS47ACJNPW.json","view_paper":"https://pith.science/paper/HDKTOLJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02827&json=true","fetch_graph":"https://pith.science/api/pith-number/HDKTOLJIOE7IEQ4JTS47ACJNPW/graph.json","fetch_events":"https://pith.science/api/pith-number/HDKTOLJIOE7IEQ4JTS47ACJNPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDKTOLJIOE7IEQ4JTS47ACJNPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDKTOLJIOE7IEQ4JTS47ACJNPW/action/storage_attestation","attest_author":"https://pith.science/pith/HDKTOLJIOE7IEQ4JTS47ACJNPW/action/author_attestation","sign_citation":"https://pith.science/pith/HDKTOLJIOE7IEQ4JTS47ACJNPW/action/citation_signature","submit_replication":"https://pith.science/pith/HDKTOLJIOE7IEQ4JTS47ACJNPW/action/replication_record"}},"created_at":"2026-07-05T11:46:35.017429+00:00","updated_at":"2026-07-05T11:46:35.017429+00:00"}