{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HJ7S5C6TE7E5IM362K7HDPP5UI","short_pith_number":"pith:HJ7S5C6T","schema_version":"1.0","canonical_sha256":"3a7f2e8bd327c9d4337ed2be71bdfda234ec27acff3e5b7710c1b0ee4855b027","source":{"kind":"arxiv","id":"2408.07268","version":1},"attestation_state":"computed","paper":{"title":"Fast Unconstrained Optimization via Hessian Averaging and Adaptive Gradient Sampling Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Raghu Bollapragada, Thomas O'Leary-Roseberry","submitted_at":"2024-08-14T03:27:48Z","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"},"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":"2408.07268","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-08-14T03:27:48Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"76b03d54d2901c1500094fcc73d108a1504c8f5b11efa875d6a3b66ee0854324","abstract_canon_sha256":"44de1c33fdb2be27479c5bf9998e911183b500b7eb2bbbfbc28a50e7369474f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:13.055901Z","signature_b64":"Vk8FxMDIX2Q/z7pD6qAMYTxVSkauaYarTvWyRgvfgaqfoFqtGF4HT2B4otyb9k0287b6/3DwwoO0VoxVmgf+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a7f2e8bd327c9d4337ed2be71bdfda234ec27acff3e5b7710c1b0ee4855b027","last_reissued_at":"2026-07-05T08:55:13.055553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:13.055553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Unconstrained Optimization via Hessian Averaging and Adaptive Gradient Sampling Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Raghu Bollapragada, Thomas O'Leary-Roseberry","submitted_at":"2024-08-14T03:27:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07268","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.07268/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2408.07268","created_at":"2026-07-05T08:55:13.055616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07268v1","created_at":"2026-07-05T08:55:13.055616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07268","created_at":"2026-07-05T08:55:13.055616+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJ7S5C6TE7E5","created_at":"2026-07-05T08:55:13.055616+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJ7S5C6TE7E5IM36","created_at":"2026-07-05T08:55:13.055616+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJ7S5C6T","created_at":"2026-07-05T08:55:13.055616+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14479","citing_title":"On the Convergence and Complexity of Proximal Gradient and Accelerated Proximal Gradient Methods under Adaptive Gradient Estimation","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJ7S5C6TE7E5IM362K7HDPP5UI","json":"https://pith.science/pith/HJ7S5C6TE7E5IM362K7HDPP5UI.json","graph_json":"https://pith.science/api/pith-number/HJ7S5C6TE7E5IM362K7HDPP5UI/graph.json","events_json":"https://pith.science/api/pith-number/HJ7S5C6TE7E5IM362K7HDPP5UI/events.json","paper":"https://pith.science/paper/HJ7S5C6T"},"agent_actions":{"view_html":"https://pith.science/pith/HJ7S5C6TE7E5IM362K7HDPP5UI","download_json":"https://pith.science/pith/HJ7S5C6TE7E5IM362K7HDPP5UI.json","view_paper":"https://pith.science/paper/HJ7S5C6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07268&json=true","fetch_graph":"https://pith.science/api/pith-number/HJ7S5C6TE7E5IM362K7HDPP5UI/graph.json","fetch_events":"https://pith.science/api/pith-number/HJ7S5C6TE7E5IM362K7HDPP5UI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJ7S5C6TE7E5IM362K7HDPP5UI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJ7S5C6TE7E5IM362K7HDPP5UI/action/storage_attestation","attest_author":"https://pith.science/pith/HJ7S5C6TE7E5IM362K7HDPP5UI/action/author_attestation","sign_citation":"https://pith.science/pith/HJ7S5C6TE7E5IM362K7HDPP5UI/action/citation_signature","submit_replication":"https://pith.science/pith/HJ7S5C6TE7E5IM362K7HDPP5UI/action/replication_record"}},"created_at":"2026-07-05T08:55:13.055616+00:00","updated_at":"2026-07-05T08:55:13.055616+00:00"}