{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XVNEJPN2VAUMFWD4BGILFFY2I6","short_pith_number":"pith:XVNEJPN2","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"},"canonical_sha256":"bd5a44bdbaa828c2d87c0990b2971a47a14eef8554c2364001300dc7e991f037","source":{"kind":"arxiv","id":"1901.00451","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.00451","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"arxiv_version","alias_value":"1901.00451v1","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00451","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"pith_short_12","alias_value":"XVNEJPN2VAUM","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XVNEJPN2VAUMFWD4","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XVNEJPN2","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XVNEJPN2VAUMFWD4BGILFFY2I6","target":"record","payload":{"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"},"canonical_sha256":"bd5a44bdbaa828c2d87c0990b2971a47a14eef8554c2364001300dc7e991f037","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"},"source_kind":"arxiv","source_id":"1901.00451","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"udHFIbf5hXFlPvuZYe9MSXD0HQRHH1WOY696/n0quaICKMWdILU/hfGslxEQfBJnyB4xLIrNhspQ1nb+AI17Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T18:54:18.867235Z"},"content_sha256":"95bc50f80ed360f15fbb13fa24d279d3471495c18eee869106c8ec5f381a2a96","schema_version":"1.0","event_id":"sha256:95bc50f80ed360f15fbb13fa24d279d3471495c18eee869106c8ec5f381a2a96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XVNEJPN2VAUMFWD4BGILFFY2I6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NQa+T0FZP1kAcVA4suhv2QPBwpmQGlJdT5wSWNSwQikwhkYkwr2Wf1xVxp/yJHhfKVsosckRwWP/dBRkF9KrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T18:54:18.867605Z"},"content_sha256":"448575fa198afab24674037a7197d2de3414c27c5426452656725eab4e775b01","schema_version":"1.0","event_id":"sha256:448575fa198afab24674037a7197d2de3414c27c5426452656725eab4e775b01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6/bundle.json","state_url":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVNEJPN2VAUMFWD4BGILFFY2I6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-21T18:54:18Z","links":{"resolver":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6","bundle":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6/bundle.json","state":"https://pith.science/pith/XVNEJPN2VAUMFWD4BGILFFY2I6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVNEJPN2VAUMFWD4BGILFFY2I6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XVNEJPN2VAUMFWD4BGILFFY2I6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8265f0125183eeb6cde2b5eece9024ae9b883fdc5569ebc2afb77444e1265ad8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-02T17:09:45Z","title_canon_sha256":"5bf06ff1ac920d8ea77c961959fb631e852749e9880b76abc6f7f1f38adcfcf2"},"schema_version":"1.0","source":{"id":"1901.00451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.00451","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"arxiv_version","alias_value":"1901.00451v1","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00451","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"pith_short_12","alias_value":"XVNEJPN2VAUM","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XVNEJPN2VAUMFWD4","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XVNEJPN2","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:448575fa198afab24674037a7197d2de3414c27c5426452656725eab4e775b01","target":"graph","created_at":"2026-05-17T23:57:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Huishuai Zhang, Junjie Yang, Vahid Tarokh, Yingbin Liang, Yi Zhou","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-02T17:09:45Z","title":"SGD Converges to Global Minimum in Deep Learning via Star-convex Path"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.00451","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:95bc50f80ed360f15fbb13fa24d279d3471495c18eee869106c8ec5f381a2a96","target":"record","created_at":"2026-05-17T23:57:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8265f0125183eeb6cde2b5eece9024ae9b883fdc5569ebc2afb77444e1265ad8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-02T17:09:45Z","title_canon_sha256":"5bf06ff1ac920d8ea77c961959fb631e852749e9880b76abc6f7f1f38adcfcf2"},"schema_version":"1.0","source":{"id":"1901.00451","kind":"arxiv","version":1}},"canonical_sha256":"bd5a44bdbaa828c2d87c0990b2971a47a14eef8554c2364001300dc7e991f037","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd5a44bdbaa828c2d87c0990b2971a47a14eef8554c2364001300dc7e991f037","first_computed_at":"2026-05-17T23:57:03.819399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:03.819399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OGx6O3m8vbzmqUMVWsvG811sxUOCSbHHTAKttOKnkr0yaO05oqidkZ/HFcka599qU6cAwIZcF55Xqi0PwPwxDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:03.820051Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.00451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95bc50f80ed360f15fbb13fa24d279d3471495c18eee869106c8ec5f381a2a96","sha256:448575fa198afab24674037a7197d2de3414c27c5426452656725eab4e775b01"],"state_sha256":"7423e1627e221492287ac0ea1284032464ab466961ebf9b727ee4316e57d6672"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W//gGzjkQqoCJeSkeKe0lxwSMraD05bQ/UrgjzNS0Ps4IJfihPz8EGOIbdHipD3WRRYHwkC20VOxZtMvbsJDDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T18:54:18.869896Z","bundle_sha256":"7309c9fc5fe31b479e94bf33909e7a4abc4cf682e68c3ba12abd7631f20c03dc"}}