{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AEIGXQLWGSRWQKCQGSCRWXHON5","short_pith_number":"pith:AEIGXQLW","schema_version":"1.0","canonical_sha256":"01106bc17634a368285034851b5cee6f5d181dc993482fb591f6c3e62c379ac9","source":{"kind":"arxiv","id":"1906.04688","version":1},"attestation_state":"computed","paper":{"title":"An Improved Analysis of Training Over-parameterized 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":"Difan Zou, Quanquan Gu","submitted_at":"2019-06-11T16:40:46Z","abstract_excerpt":"A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the condition on the width of the neural network to ensure the global convergence is very stringent, which is often a high-degree polynomial in the training sample size $n$ (e.g., $O(n^{24})$). In this paper, we provide an improved analysis of the global convergence of (stochastic) gradient descent for training deep neural networks, which only requires a milder over-pa"},"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":"1906.04688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T16:40:46Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"b90ae8a03904423baf3620d759daf9070269c2330148647d19c38ece26f66fb7","abstract_canon_sha256":"667fe11f96283cd4cbf5038589136bd145ff46706dce5d84c1a60aef9ba95fd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:33.750758Z","signature_b64":"ufxT8DALDr//zqnJn9QU+5zRXJ4AWB30XnZztGxfCbJ/nOHQsQpUV9j0ALFzbwtTqvqeTaTSm2GTVS81qUN1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01106bc17634a368285034851b5cee6f5d181dc993482fb591f6c3e62c379ac9","last_reissued_at":"2026-05-17T23:43:33.750296Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:33.750296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Improved Analysis of Training Over-parameterized 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":"Difan Zou, Quanquan Gu","submitted_at":"2019-06-11T16:40:46Z","abstract_excerpt":"A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the condition on the width of the neural network to ensure the global convergence is very stringent, which is often a high-degree polynomial in the training sample size $n$ (e.g., $O(n^{24})$). In this paper, we provide an improved analysis of the global convergence of (stochastic) gradient descent for training deep neural networks, which only requires a milder over-pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04688","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":""},"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":"1906.04688","created_at":"2026-05-17T23:43:33.750377+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04688v1","created_at":"2026-05-17T23:43:33.750377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04688","created_at":"2026-05-17T23:43:33.750377+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEIGXQLWGSRW","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEIGXQLWGSRWQKCQ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEIGXQLW","created_at":"2026-05-18T12:33:12.712433+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/AEIGXQLWGSRWQKCQGSCRWXHON5","json":"https://pith.science/pith/AEIGXQLWGSRWQKCQGSCRWXHON5.json","graph_json":"https://pith.science/api/pith-number/AEIGXQLWGSRWQKCQGSCRWXHON5/graph.json","events_json":"https://pith.science/api/pith-number/AEIGXQLWGSRWQKCQGSCRWXHON5/events.json","paper":"https://pith.science/paper/AEIGXQLW"},"agent_actions":{"view_html":"https://pith.science/pith/AEIGXQLWGSRWQKCQGSCRWXHON5","download_json":"https://pith.science/pith/AEIGXQLWGSRWQKCQGSCRWXHON5.json","view_paper":"https://pith.science/paper/AEIGXQLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04688&json=true","fetch_graph":"https://pith.science/api/pith-number/AEIGXQLWGSRWQKCQGSCRWXHON5/graph.json","fetch_events":"https://pith.science/api/pith-number/AEIGXQLWGSRWQKCQGSCRWXHON5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEIGXQLWGSRWQKCQGSCRWXHON5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEIGXQLWGSRWQKCQGSCRWXHON5/action/storage_attestation","attest_author":"https://pith.science/pith/AEIGXQLWGSRWQKCQGSCRWXHON5/action/author_attestation","sign_citation":"https://pith.science/pith/AEIGXQLWGSRWQKCQGSCRWXHON5/action/citation_signature","submit_replication":"https://pith.science/pith/AEIGXQLWGSRWQKCQGSCRWXHON5/action/replication_record"}},"created_at":"2026-05-17T23:43:33.750377+00:00","updated_at":"2026-05-17T23:43:33.750377+00:00"}