{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OBWJJAUSTHRYO7ZQ3V2OSG6TMC","short_pith_number":"pith:OBWJJAUS","schema_version":"1.0","canonical_sha256":"706c94829299e3877f30dd74e91bd360b0042e5c59fb05ea9ee0d5f91354805d","source":{"kind":"arxiv","id":"2312.03807","version":3},"attestation_state":"computed","paper":{"title":"Achieving ${O}(\\epsilon^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Kaiyi Ji, Peiyao Xiao, Yifan Yang","submitted_at":"2023-12-06T16:34:58Z","abstract_excerpt":"In this paper, we revisit the bilevel optimization problem, in which the upper-level objective function is generally nonconvex and the lower-level objective function is strongly convex. Although this type of problem has been studied extensively, it still remains an open question how to achieve an ${O}(\\epsilon^{-1.5})$ sample complexity in Hessian/Jacobian-free stochastic bilevel optimization without any second-order derivative computation. To fill this gap, we propose a novel Hessian/Jacobian-free bilevel optimizer named FdeHBO, which features a simple fully single-loop structure, a projectio"},"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":"2312.03807","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-12-06T16:34:58Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"244898719782a0a4e8a50f02077abf4b672cd6458e6d6eb23ec456e38baa3f13","abstract_canon_sha256":"52045b1a924b15b0198e0f03b284bf2ce5bd3ccd2fae085df5607aeec19a9411"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:05.530394Z","signature_b64":"EeibPtWY/c0OjOs4KOxv6anYR+ll6kl+LWqR0cV7CQY59z1BGJ4Hl4lqJKhbXrNGKRuOlEcylIsHM9F0dr/lDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"706c94829299e3877f30dd74e91bd360b0042e5c59fb05ea9ee0d5f91354805d","last_reissued_at":"2026-07-05T10:45:05.529758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:05.529758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Achieving ${O}(\\epsilon^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Kaiyi Ji, Peiyao Xiao, Yifan Yang","submitted_at":"2023-12-06T16:34:58Z","abstract_excerpt":"In this paper, we revisit the bilevel optimization problem, in which the upper-level objective function is generally nonconvex and the lower-level objective function is strongly convex. Although this type of problem has been studied extensively, it still remains an open question how to achieve an ${O}(\\epsilon^{-1.5})$ sample complexity in Hessian/Jacobian-free stochastic bilevel optimization without any second-order derivative computation. To fill this gap, we propose a novel Hessian/Jacobian-free bilevel optimizer named FdeHBO, which features a simple fully single-loop structure, a projectio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03807","kind":"arxiv","version":3},"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/2312.03807/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":"2312.03807","created_at":"2026-07-05T10:45:05.529841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03807v3","created_at":"2026-07-05T10:45:05.529841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03807","created_at":"2026-07-05T10:45:05.529841+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBWJJAUSTHRY","created_at":"2026-07-05T10:45:05.529841+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBWJJAUSTHRYO7ZQ","created_at":"2026-07-05T10:45:05.529841+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBWJJAUS","created_at":"2026-07-05T10:45:05.529841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.01126","citing_title":"Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBWJJAUSTHRYO7ZQ3V2OSG6TMC","json":"https://pith.science/pith/OBWJJAUSTHRYO7ZQ3V2OSG6TMC.json","graph_json":"https://pith.science/api/pith-number/OBWJJAUSTHRYO7ZQ3V2OSG6TMC/graph.json","events_json":"https://pith.science/api/pith-number/OBWJJAUSTHRYO7ZQ3V2OSG6TMC/events.json","paper":"https://pith.science/paper/OBWJJAUS"},"agent_actions":{"view_html":"https://pith.science/pith/OBWJJAUSTHRYO7ZQ3V2OSG6TMC","download_json":"https://pith.science/pith/OBWJJAUSTHRYO7ZQ3V2OSG6TMC.json","view_paper":"https://pith.science/paper/OBWJJAUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03807&json=true","fetch_graph":"https://pith.science/api/pith-number/OBWJJAUSTHRYO7ZQ3V2OSG6TMC/graph.json","fetch_events":"https://pith.science/api/pith-number/OBWJJAUSTHRYO7ZQ3V2OSG6TMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBWJJAUSTHRYO7ZQ3V2OSG6TMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBWJJAUSTHRYO7ZQ3V2OSG6TMC/action/storage_attestation","attest_author":"https://pith.science/pith/OBWJJAUSTHRYO7ZQ3V2OSG6TMC/action/author_attestation","sign_citation":"https://pith.science/pith/OBWJJAUSTHRYO7ZQ3V2OSG6TMC/action/citation_signature","submit_replication":"https://pith.science/pith/OBWJJAUSTHRYO7ZQ3V2OSG6TMC/action/replication_record"}},"created_at":"2026-07-05T10:45:05.529841+00:00","updated_at":"2026-07-05T10:45:05.529841+00:00"}