{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DTZK5XBCOSMSW47DDYEXE6ZU6T","short_pith_number":"pith:DTZK5XBC","schema_version":"1.0","canonical_sha256":"1cf2aedc2274992b73e31e09727b34f4e23da7e0bc9bf845ab9aa18f07e69131","source":{"kind":"arxiv","id":"2407.07670","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Gradient Descent for Two-layer Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dinghao Cao, Lei Shi, Zheng-Chu Guo","submitted_at":"2024-07-10T13:58:57Z","abstract_excerpt":"This paper presents a comprehensive study on the convergence rates of the stochastic gradient descent (SGD) algorithm when applied to overparameterized two-layer neural networks. Our approach combines the Neural Tangent Kernel (NTK) approximation with convergence analysis in the Reproducing Kernel Hilbert Space (RKHS) generated by NTK, aiming to provide a deep understanding of the convergence behavior of SGD in overparameterized two-layer neural networks. Our research framework enables us to explore the intricate interplay between kernel methods and optimization processes, shedding light on th"},"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":"2407.07670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-07-10T13:58:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2380e235d04b0567e9ef4e2ab0225b13ff33de88fd21dfa38476eae5439ec8e5","abstract_canon_sha256":"78ee954548ce32c9797a0ef0b23f47a746da8f748bab88f329148b74e3cb1bd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:23.964834Z","signature_b64":"a4WuwiSgwU9bgih2rGzAW40dK59iZrSa7nbu5jfPEBdjYE8sU+M7yHDaDzeEXg9Izo7xEWBeqon8UVdiS+j7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cf2aedc2274992b73e31e09727b34f4e23da7e0bc9bf845ab9aa18f07e69131","last_reissued_at":"2026-07-05T08:42:23.964372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:23.964372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Gradient Descent for Two-layer Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dinghao Cao, Lei Shi, Zheng-Chu Guo","submitted_at":"2024-07-10T13:58:57Z","abstract_excerpt":"This paper presents a comprehensive study on the convergence rates of the stochastic gradient descent (SGD) algorithm when applied to overparameterized two-layer neural networks. Our approach combines the Neural Tangent Kernel (NTK) approximation with convergence analysis in the Reproducing Kernel Hilbert Space (RKHS) generated by NTK, aiming to provide a deep understanding of the convergence behavior of SGD in overparameterized two-layer neural networks. Our research framework enables us to explore the intricate interplay between kernel methods and optimization processes, shedding light on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07670","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/2407.07670/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":"2407.07670","created_at":"2026-07-05T08:42:23.964437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07670v1","created_at":"2026-07-05T08:42:23.964437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07670","created_at":"2026-07-05T08:42:23.964437+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTZK5XBCOSMS","created_at":"2026-07-05T08:42:23.964437+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTZK5XBCOSMSW47D","created_at":"2026-07-05T08:42:23.964437+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTZK5XBC","created_at":"2026-07-05T08:42:23.964437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06772","citing_title":"Minimax-Optimal Generalization Bounds for Smooth Deep Neural Networks Trained by (Stochastic) Gradient Descent","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06764","citing_title":"Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DTZK5XBCOSMSW47DDYEXE6ZU6T","json":"https://pith.science/pith/DTZK5XBCOSMSW47DDYEXE6ZU6T.json","graph_json":"https://pith.science/api/pith-number/DTZK5XBCOSMSW47DDYEXE6ZU6T/graph.json","events_json":"https://pith.science/api/pith-number/DTZK5XBCOSMSW47DDYEXE6ZU6T/events.json","paper":"https://pith.science/paper/DTZK5XBC"},"agent_actions":{"view_html":"https://pith.science/pith/DTZK5XBCOSMSW47DDYEXE6ZU6T","download_json":"https://pith.science/pith/DTZK5XBCOSMSW47DDYEXE6ZU6T.json","view_paper":"https://pith.science/paper/DTZK5XBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07670&json=true","fetch_graph":"https://pith.science/api/pith-number/DTZK5XBCOSMSW47DDYEXE6ZU6T/graph.json","fetch_events":"https://pith.science/api/pith-number/DTZK5XBCOSMSW47DDYEXE6ZU6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTZK5XBCOSMSW47DDYEXE6ZU6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTZK5XBCOSMSW47DDYEXE6ZU6T/action/storage_attestation","attest_author":"https://pith.science/pith/DTZK5XBCOSMSW47DDYEXE6ZU6T/action/author_attestation","sign_citation":"https://pith.science/pith/DTZK5XBCOSMSW47DDYEXE6ZU6T/action/citation_signature","submit_replication":"https://pith.science/pith/DTZK5XBCOSMSW47DDYEXE6ZU6T/action/replication_record"}},"created_at":"2026-07-05T08:42:23.964437+00:00","updated_at":"2026-07-05T08:42:23.964437+00:00"}