{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XVNEJPN2VAUMFWD4BGILFFY2I6","short_pith_number":"pith:XVNEJPN2","schema_version":"1.0","canonical_sha256":"bd5a44bdbaa828c2d87c0990b2971a47a14eef8554c2364001300dc7e991f037","source":{"kind":"arxiv","id":"1901.00451","version":1},"attestation_state":"computed","paper":{"title":"SGD Converges to Global Minimum in Deep Learning via Star-convex Path","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huishuai Zhang, Junjie Yang, Vahid Tarokh, Yingbin Liang, Yi Zhou","submitted_at":"2019-01-02T17:09:45Z","abstract_excerpt":"Stochastic gradient descent (SGD) has been found to be surprisingly effective in training a variety of deep neural networks. However, there is still a lack of understanding on how and why SGD can train these complex networks towards a global minimum. In this study, we establish the convergence of SGD to a global minimum for nonconvex optimization problems that are commonly encountered in neural network training. Our argument exploits the following two important properties: 1) the training loss can achieve zero value (approximately), which has been widely observed in deep learning; 2) SGD follo"},"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":"1901.00451","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-02T17:09:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5bf06ff1ac920d8ea77c961959fb631e852749e9880b76abc6f7f1f38adcfcf2","abstract_canon_sha256":"8265f0125183eeb6cde2b5eece9024ae9b883fdc5569ebc2afb77444e1265ad8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:03.820051Z","signature_b64":"OGx6O3m8vbzmqUMVWsvG811sxUOCSbHHTAKttOKnkr0yaO05oqidkZ/HFcka599qU6cAwIZcF55Xqi0PwPwxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd5a44bdbaa828c2d87c0990b2971a47a14eef8554c2364001300dc7e991f037","last_reissued_at":"2026-05-17T23:57:03.819399Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:03.819399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SGD Converges to Global Minimum in Deep Learning via Star-convex Path","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huishuai Zhang, Junjie Yang, Vahid Tarokh, Yingbin Liang, Yi Zhou","submitted_at":"2019-01-02T17:09:45Z","abstract_excerpt":"Stochastic gradient descent (SGD) has been found to be surprisingly effective in training a variety of deep neural networks. However, there is still a lack of understanding on how and why SGD can train these complex networks towards a global minimum. In this study, we establish the convergence of SGD to a global minimum for nonconvex optimization problems that are commonly encountered in neural network training. Our argument exploits the following two important properties: 1) the training loss can achieve zero value (approximately), which has been widely observed in deep learning; 2) SGD follo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.00451","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":"1901.00451","created_at":"2026-05-17T23:57:03.819508+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.00451v1","created_at":"2026-05-17T23:57:03.819508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00451","created_at":"2026-05-17T23:57:03.819508+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVNEJPN2VAUM","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVNEJPN2VAUMFWD4","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVNEJPN2","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.15522","citing_title":"Stochastic Non-Smooth Convex Optimization with Unbounded Gradients","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2505.23737","citing_title":"On the Convergence Analysis of Muon","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14017","citing_title":"Stochastic Trust-Region Methods for Over-parameterized Models","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6","json":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6.json","graph_json":"https://pith.science/api/pith-number/XVNEJPN2VAUMFWD4BGILFFY2I6/graph.json","events_json":"https://pith.science/api/pith-number/XVNEJPN2VAUMFWD4BGILFFY2I6/events.json","paper":"https://pith.science/paper/XVNEJPN2"},"agent_actions":{"view_html":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6","download_json":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6.json","view_paper":"https://pith.science/paper/XVNEJPN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.00451&json=true","fetch_graph":"https://pith.science/api/pith-number/XVNEJPN2VAUMFWD4BGILFFY2I6/graph.json","fetch_events":"https://pith.science/api/pith-number/XVNEJPN2VAUMFWD4BGILFFY2I6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6/action/storage_attestation","attest_author":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6/action/author_attestation","sign_citation":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6/action/citation_signature","submit_replication":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6/action/replication_record"}},"created_at":"2026-05-17T23:57:03.819508+00:00","updated_at":"2026-05-17T23:57:03.819508+00:00"}