{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HJ7S5C6TE7E5IM362K7HDPP5UI","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":"44de1c33fdb2be27479c5bf9998e911183b500b7eb2bbbfbc28a50e7369474f4","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-08-14T03:27:48Z","title_canon_sha256":"76b03d54d2901c1500094fcc73d108a1504c8f5b11efa875d6a3b66ee0854324"},"schema_version":"1.0","source":{"id":"2408.07268","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07268","created_at":"2026-07-05T08:55:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07268v1","created_at":"2026-07-05T08:55:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07268","created_at":"2026-07-05T08:55:13Z"},{"alias_kind":"pith_short_12","alias_value":"HJ7S5C6TE7E5","created_at":"2026-07-05T08:55:13Z"},{"alias_kind":"pith_short_16","alias_value":"HJ7S5C6TE7E5IM36","created_at":"2026-07-05T08:55:13Z"},{"alias_kind":"pith_short_8","alias_value":"HJ7S5C6T","created_at":"2026-07-05T08:55:13Z"}],"graph_snapshots":[{"event_id":"sha256:9ef14d6ff7767db2557dce98faedf6fe8d091d60fdf8c2d63cbc33a0f1ad2cc8","target":"graph","created_at":"2026-07-05T08:55:13Z","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/2408.07268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider minimizing finite-sum and expectation objective functions via Hessian-averaging based subsampled Newton methods. These methods allow for gradient inexactness and have fixed per-iteration Hessian approximation costs. The recent work (Na et al. 2023) demonstrated that Hessian averaging can be utilized to achieve fast $\\mathcal{O}\\left(\\sqrt{\\tfrac{\\log k}{k}}\\right)$ local superlinear convergence for strongly convex functions in high probability, while maintaining fixed per-iteration Hessian costs. These methods, however, require gradient exactness and strong convexity, which poses c","authors_text":"Raghu Bollapragada, Thomas O'Leary-Roseberry","cross_cats":["cs.NA","math.NA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-08-14T03:27:48Z","title":"Fast Unconstrained Optimization via Hessian Averaging and Adaptive Gradient Sampling Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07268","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:c92f43ea33ece2ba21b53859e3c84437a84b7cb44d3f3614356d255faa3fea27","target":"record","created_at":"2026-07-05T08:55:13Z","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":"44de1c33fdb2be27479c5bf9998e911183b500b7eb2bbbfbc28a50e7369474f4","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-08-14T03:27:48Z","title_canon_sha256":"76b03d54d2901c1500094fcc73d108a1504c8f5b11efa875d6a3b66ee0854324"},"schema_version":"1.0","source":{"id":"2408.07268","kind":"arxiv","version":1}},"canonical_sha256":"3a7f2e8bd327c9d4337ed2be71bdfda234ec27acff3e5b7710c1b0ee4855b027","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a7f2e8bd327c9d4337ed2be71bdfda234ec27acff3e5b7710c1b0ee4855b027","first_computed_at":"2026-07-05T08:55:13.055553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:13.055553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vk8FxMDIX2Q/z7pD6qAMYTxVSkauaYarTvWyRgvfgaqfoFqtGF4HT2B4otyb9k0287b6/3DwwoO0VoxVmgf+CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:13.055901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07268","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c92f43ea33ece2ba21b53859e3c84437a84b7cb44d3f3614356d255faa3fea27","sha256:9ef14d6ff7767db2557dce98faedf6fe8d091d60fdf8c2d63cbc33a0f1ad2cc8"],"state_sha256":"7c91d07e530d2b80844e2473fb2cc0ed24ff67d3227e0ef1e5d982a2824a199a"}