{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KWGXOPCCBVQQDOMMTUWXD6N2BI","short_pith_number":"pith:KWGXOPCC","schema_version":"1.0","canonical_sha256":"558d773c420d6101b98c9d2d71f9ba0a33cd2e5da450d25b01bb4a1fefb1b8f4","source":{"kind":"arxiv","id":"2304.09221","version":2},"attestation_state":"computed","paper":{"title":"Convergence of stochastic gradient descent under a local Lojasiewicz condition for deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianfeng Lu, Jing An","submitted_at":"2023-04-18T18:20:52Z","abstract_excerpt":"We study the convergence of stochastic gradient descent (SGD) for non-convex objective functions. We establish the local convergence with positive probability under the local \\L{}ojasiewicz condition introduced by Chatterjee in \\cite{chatterjee2022convergence} and an additional local structural assumption of the loss function landscape. A key component of our proof is to ensure that the whole trajectories of SGD stay inside the local region with a positive probability. We also provide examples of neural networks with finite widths such that our assumptions hold."},"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":"2304.09221","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-18T18:20:52Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"baf541633b89717355a0424b7d4893a5d4145d55528313cac2f1f2303c2e0c25","abstract_canon_sha256":"9e352bec8fa65733cddabc746d10ab86a6407bd0a669807f6b9685814598ec6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:12.274010Z","signature_b64":"fqMV6c3h0k5YxjglnavO0lRidcI7LkBSr/42ir2r+jK7MenHsJuKArE+ZufmpGiiKm0c13aDFklurGCL9BjwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"558d773c420d6101b98c9d2d71f9ba0a33cd2e5da450d25b01bb4a1fefb1b8f4","last_reissued_at":"2026-07-05T07:33:12.273551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:12.273551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of stochastic gradient descent under a local Lojasiewicz condition for deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianfeng Lu, Jing An","submitted_at":"2023-04-18T18:20:52Z","abstract_excerpt":"We study the convergence of stochastic gradient descent (SGD) for non-convex objective functions. We establish the local convergence with positive probability under the local \\L{}ojasiewicz condition introduced by Chatterjee in \\cite{chatterjee2022convergence} and an additional local structural assumption of the loss function landscape. A key component of our proof is to ensure that the whole trajectories of SGD stay inside the local region with a positive probability. We also provide examples of neural networks with finite widths such that our assumptions hold."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09221","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/2304.09221/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":"2304.09221","created_at":"2026-07-05T07:33:12.273606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.09221v2","created_at":"2026-07-05T07:33:12.273606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09221","created_at":"2026-07-05T07:33:12.273606+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWGXOPCCBVQQ","created_at":"2026-07-05T07:33:12.273606+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWGXOPCCBVQQDOMM","created_at":"2026-07-05T07:33:12.273606+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWGXOPCC","created_at":"2026-07-05T07:33:12.273606+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21429","citing_title":"From Sublinear to Linear: Local Convergence in Finite-Width Networks via Locally Polyak-Lojasiewicz Regions","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWGXOPCCBVQQDOMMTUWXD6N2BI","json":"https://pith.science/pith/KWGXOPCCBVQQDOMMTUWXD6N2BI.json","graph_json":"https://pith.science/api/pith-number/KWGXOPCCBVQQDOMMTUWXD6N2BI/graph.json","events_json":"https://pith.science/api/pith-number/KWGXOPCCBVQQDOMMTUWXD6N2BI/events.json","paper":"https://pith.science/paper/KWGXOPCC"},"agent_actions":{"view_html":"https://pith.science/pith/KWGXOPCCBVQQDOMMTUWXD6N2BI","download_json":"https://pith.science/pith/KWGXOPCCBVQQDOMMTUWXD6N2BI.json","view_paper":"https://pith.science/paper/KWGXOPCC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.09221&json=true","fetch_graph":"https://pith.science/api/pith-number/KWGXOPCCBVQQDOMMTUWXD6N2BI/graph.json","fetch_events":"https://pith.science/api/pith-number/KWGXOPCCBVQQDOMMTUWXD6N2BI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWGXOPCCBVQQDOMMTUWXD6N2BI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWGXOPCCBVQQDOMMTUWXD6N2BI/action/storage_attestation","attest_author":"https://pith.science/pith/KWGXOPCCBVQQDOMMTUWXD6N2BI/action/author_attestation","sign_citation":"https://pith.science/pith/KWGXOPCCBVQQDOMMTUWXD6N2BI/action/citation_signature","submit_replication":"https://pith.science/pith/KWGXOPCCBVQQDOMMTUWXD6N2BI/action/replication_record"}},"created_at":"2026-07-05T07:33:12.273606+00:00","updated_at":"2026-07-05T07:33:12.273606+00:00"}