{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IA7DKZOABHOFNQHWMXKLBXSZ3D","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":"b48f4b6e2522cc461f8b550afd07f9ae82703c75d161858c157e1bd152e0f215","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-02T05:24:05Z","title_canon_sha256":"63234f58c094a1a23145c8f3fc551dbaede326b7314546933a09e3a372f80f35"},"schema_version":"1.0","source":{"id":"2112.00987","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.00987","created_at":"2026-07-05T03:37:02Z"},{"alias_kind":"arxiv_version","alias_value":"2112.00987v1","created_at":"2026-07-05T03:37:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00987","created_at":"2026-07-05T03:37:02Z"},{"alias_kind":"pith_short_12","alias_value":"IA7DKZOABHOF","created_at":"2026-07-05T03:37:02Z"},{"alias_kind":"pith_short_16","alias_value":"IA7DKZOABHOFNQHW","created_at":"2026-07-05T03:37:02Z"},{"alias_kind":"pith_short_8","alias_value":"IA7DKZOA","created_at":"2026-07-05T03:37:02Z"}],"graph_snapshots":[{"event_id":"sha256:d557277aaf77bc1ac8e0df029482633c4b31334e884eaf10d32fec13c989404f","target":"graph","created_at":"2026-07-05T03:37:02Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.00987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the statistical properties of the dynamic trajectory of stochastic gradient descent (SGD). We approximate the mini-batch SGD and the momentum SGD as stochastic differential equations (SDEs). We exploit the continuous formulation of SDE and the theory of Fokker-Planck equations to develop new results on the escaping phenomenon and the relationship with large batch and sharp minima. In particular, we find that the stochastic process solution tends to converge to flatter minima regardless of the batch size in the asymptotic regime. However, the convergence rate is rigorously proven to de","authors_text":"Xiaowu Dai, Yuhua Zhu","cross_cats":["math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-02T05:24:05Z","title":"On Large Batch Training and Sharp Minima: A Fokker-Planck Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00987","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":"sha256:11146006bc8f2037932cf897439a5d060b401d2f285f8b86b48ec9583aa52c58","target":"record","created_at":"2026-07-05T03:37:02Z","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":"b48f4b6e2522cc461f8b550afd07f9ae82703c75d161858c157e1bd152e0f215","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-02T05:24:05Z","title_canon_sha256":"63234f58c094a1a23145c8f3fc551dbaede326b7314546933a09e3a372f80f35"},"schema_version":"1.0","source":{"id":"2112.00987","kind":"arxiv","version":1}},"canonical_sha256":"403e3565c009dc56c0f665d4b0de59d8e33f7acfaf42c670d7c5c04ca87f9edc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"403e3565c009dc56c0f665d4b0de59d8e33f7acfaf42c670d7c5c04ca87f9edc","first_computed_at":"2026-07-05T03:37:02.272919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:02.272919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ERuVckQtHYr4mvnnQBq8QjdLODIi9/b/BjWW6PBnkVRGfB2DF7sA/g0xOTV03Hy/f3HQUBXw/YSRHqHqTvZ9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:02.273395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.00987","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11146006bc8f2037932cf897439a5d060b401d2f285f8b86b48ec9583aa52c58","sha256:d557277aaf77bc1ac8e0df029482633c4b31334e884eaf10d32fec13c989404f"],"state_sha256":"94a7add814e6ba82ea4e585940290dccd1494d5fae345c1c6796d39436d26408"}