{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UIZRNH3YBIMRPO5VKIDPZ4RA7X","short_pith_number":"pith:UIZRNH3Y","schema_version":"1.0","canonical_sha256":"a233169f780a1917bbb55206fcf220fddde3b10e1ada6ebf700efe9c13a4304f","source":{"kind":"arxiv","id":"1809.09853","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Second-order Methods for Non-convex Optimization with Inexact Hessian and Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Cho-Jui Hsieh, Dacheng Tao, Liu Liu, Xuanqing Liu","submitted_at":"2018-09-26T08:59:09Z","abstract_excerpt":"Trust region and cubic regularization methods have demonstrated good performance in small scale non-convex optimization, showing the ability to escape from saddle points. Each iteration of these methods involves computation of gradient, Hessian and function value in order to obtain the search direction and adjust the radius or cubic regularization parameter. However, exactly computing those quantities are too expensive in large-scale problems such as training deep networks. In this paper, we study a family of stochastic trust region and cubic regularization methods when gradient, Hessian and f"},"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":"1809.09853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-26T08:59:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"8a23d4eefb13cebf9d215cd335572210b6516a923aea6029414d1028be18c31e","abstract_canon_sha256":"d652572d9f36242b2aaf6a9a21fbb165553d3ee5e113860140ccaef5d7077ca1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:43.469784Z","signature_b64":"hcPDtlTLUf4OknzvirXM+/jFKuK8TdUw2xsj2QH34TazfknctC6jxrdi3LCPeCltuOQy+Ksv+aLof/ttkaWnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a233169f780a1917bbb55206fcf220fddde3b10e1ada6ebf700efe9c13a4304f","last_reissued_at":"2026-05-18T00:04:43.468998Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:43.468998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Second-order Methods for Non-convex Optimization with Inexact Hessian and Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Cho-Jui Hsieh, Dacheng Tao, Liu Liu, Xuanqing Liu","submitted_at":"2018-09-26T08:59:09Z","abstract_excerpt":"Trust region and cubic regularization methods have demonstrated good performance in small scale non-convex optimization, showing the ability to escape from saddle points. Each iteration of these methods involves computation of gradient, Hessian and function value in order to obtain the search direction and adjust the radius or cubic regularization parameter. However, exactly computing those quantities are too expensive in large-scale problems such as training deep networks. In this paper, we study a family of stochastic trust region and cubic regularization methods when gradient, Hessian and f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09853","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":"1809.09853","created_at":"2026-05-18T00:04:43.469125+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.09853v1","created_at":"2026-05-18T00:04:43.469125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09853","created_at":"2026-05-18T00:04:43.469125+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIZRNH3YBIMR","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIZRNH3YBIMRPO5V","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIZRNH3Y","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UIZRNH3YBIMRPO5VKIDPZ4RA7X","json":"https://pith.science/pith/UIZRNH3YBIMRPO5VKIDPZ4RA7X.json","graph_json":"https://pith.science/api/pith-number/UIZRNH3YBIMRPO5VKIDPZ4RA7X/graph.json","events_json":"https://pith.science/api/pith-number/UIZRNH3YBIMRPO5VKIDPZ4RA7X/events.json","paper":"https://pith.science/paper/UIZRNH3Y"},"agent_actions":{"view_html":"https://pith.science/pith/UIZRNH3YBIMRPO5VKIDPZ4RA7X","download_json":"https://pith.science/pith/UIZRNH3YBIMRPO5VKIDPZ4RA7X.json","view_paper":"https://pith.science/paper/UIZRNH3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.09853&json=true","fetch_graph":"https://pith.science/api/pith-number/UIZRNH3YBIMRPO5VKIDPZ4RA7X/graph.json","fetch_events":"https://pith.science/api/pith-number/UIZRNH3YBIMRPO5VKIDPZ4RA7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIZRNH3YBIMRPO5VKIDPZ4RA7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIZRNH3YBIMRPO5VKIDPZ4RA7X/action/storage_attestation","attest_author":"https://pith.science/pith/UIZRNH3YBIMRPO5VKIDPZ4RA7X/action/author_attestation","sign_citation":"https://pith.science/pith/UIZRNH3YBIMRPO5VKIDPZ4RA7X/action/citation_signature","submit_replication":"https://pith.science/pith/UIZRNH3YBIMRPO5VKIDPZ4RA7X/action/replication_record"}},"created_at":"2026-05-18T00:04:43.469125+00:00","updated_at":"2026-05-18T00:04:43.469125+00:00"}