{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5OQ6SXW76YJ7VPFLLBLDKKFCAX","short_pith_number":"pith:5OQ6SXW7","schema_version":"1.0","canonical_sha256":"eba1e95edff613fabcab58563528a205c5f68de318b73eacdbce12b8b2b3108e","source":{"kind":"arxiv","id":"2301.10945","version":1},"attestation_state":"computed","paper":{"title":"A Fully First-Order Method for Stochastic Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"math.OC","authors_text":"Dohyun Kwon, Jeongyeol Kwon, Robert Nowak, Stephen Wright","submitted_at":"2023-01-26T05:34:21Z","abstract_excerpt":"We consider stochastic unconstrained bilevel optimization problems when only the first-order gradient oracles are available. While numerous optimization methods have been proposed for tackling bilevel problems, existing methods either tend to require possibly expensive calculations regarding Hessians of lower-level objectives, or lack rigorous finite-time performance guarantees. In this work, we propose a Fully First-order Stochastic Approximation (F2SA) method, and study its non-asymptotic convergence properties. Specifically, we show that F2SA converges to an $\\epsilon$-stationary solution o"},"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":"2301.10945","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-01-26T05:34:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"06e97fca3540be2f845d12a6ef6d169a1a84df8f4d0486165fa80d85ee8f1e27","abstract_canon_sha256":"505cb28c08876bd0bbb2e1201618ef8f2911ccf29ad2784bcfb8c5357ea81b18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:08.342968Z","signature_b64":"Mrx5hi6Ro2flsyMC3QFgqc3V4NGptBJNjfWHvdHzGfCER0tW9N8kz6Ibf4AF9HHz3o/gEB4MUfITJYoZzSqaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eba1e95edff613fabcab58563528a205c5f68de318b73eacdbce12b8b2b3108e","last_reissued_at":"2026-07-05T05:36:08.342417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:08.342417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Fully First-Order Method for Stochastic Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"math.OC","authors_text":"Dohyun Kwon, Jeongyeol Kwon, Robert Nowak, Stephen Wright","submitted_at":"2023-01-26T05:34:21Z","abstract_excerpt":"We consider stochastic unconstrained bilevel optimization problems when only the first-order gradient oracles are available. While numerous optimization methods have been proposed for tackling bilevel problems, existing methods either tend to require possibly expensive calculations regarding Hessians of lower-level objectives, or lack rigorous finite-time performance guarantees. In this work, we propose a Fully First-order Stochastic Approximation (F2SA) method, and study its non-asymptotic convergence properties. Specifically, we show that F2SA converges to an $\\epsilon$-stationary solution o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10945","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/2301.10945/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":"2301.10945","created_at":"2026-07-05T05:36:08.342479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.10945v1","created_at":"2026-07-05T05:36:08.342479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10945","created_at":"2026-07-05T05:36:08.342479+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OQ6SXW76YJ7","created_at":"2026-07-05T05:36:08.342479+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OQ6SXW76YJ7VPFL","created_at":"2026-07-05T05:36:08.342479+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OQ6SXW7","created_at":"2026-07-05T05:36:08.342479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21598","citing_title":"Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5OQ6SXW76YJ7VPFLLBLDKKFCAX","json":"https://pith.science/pith/5OQ6SXW76YJ7VPFLLBLDKKFCAX.json","graph_json":"https://pith.science/api/pith-number/5OQ6SXW76YJ7VPFLLBLDKKFCAX/graph.json","events_json":"https://pith.science/api/pith-number/5OQ6SXW76YJ7VPFLLBLDKKFCAX/events.json","paper":"https://pith.science/paper/5OQ6SXW7"},"agent_actions":{"view_html":"https://pith.science/pith/5OQ6SXW76YJ7VPFLLBLDKKFCAX","download_json":"https://pith.science/pith/5OQ6SXW76YJ7VPFLLBLDKKFCAX.json","view_paper":"https://pith.science/paper/5OQ6SXW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.10945&json=true","fetch_graph":"https://pith.science/api/pith-number/5OQ6SXW76YJ7VPFLLBLDKKFCAX/graph.json","fetch_events":"https://pith.science/api/pith-number/5OQ6SXW76YJ7VPFLLBLDKKFCAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OQ6SXW76YJ7VPFLLBLDKKFCAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OQ6SXW76YJ7VPFLLBLDKKFCAX/action/storage_attestation","attest_author":"https://pith.science/pith/5OQ6SXW76YJ7VPFLLBLDKKFCAX/action/author_attestation","sign_citation":"https://pith.science/pith/5OQ6SXW76YJ7VPFLLBLDKKFCAX/action/citation_signature","submit_replication":"https://pith.science/pith/5OQ6SXW76YJ7VPFLLBLDKKFCAX/action/replication_record"}},"created_at":"2026-07-05T05:36:08.342479+00:00","updated_at":"2026-07-05T05:36:08.342479+00:00"}