{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RNLM63YGOMK7FJ7TG7VBWH2SZX","short_pith_number":"pith:RNLM63YG","schema_version":"1.0","canonical_sha256":"8b56cf6f067315f2a7f337ea1b1f52cdccb558013653b0f0a3323c0dd5d4d74e","source":{"kind":"arxiv","id":"2406.12771","version":2},"attestation_state":"computed","paper":{"title":"First-Order Methods for Linearly Constrained Bilevel Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Guy Kornowski, Kai Wang, Suvrit Sra, Swati Padmanabhan, Zhe Zhang","submitted_at":"2024-06-18T16:41:21Z","abstract_excerpt":"Algorithms for bilevel optimization often encounter Hessian computations, which are prohibitive in high dimensions. While recent works offer first-order methods for unconstrained bilevel problems, the constrained setting remains relatively underexplored. We present first-order linearly constrained optimization methods with finite-time hypergradient stationarity guarantees. For linear equality constraints, we attain $\\epsilon$-stationarity in $\\widetilde{O}(\\epsilon^{-2})$ gradient oracle calls, which is nearly-optimal. For linear inequality constraints, we attain $(\\delta,\\epsilon)$-Goldstein "},"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":"2406.12771","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-06-18T16:41:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5fc24ee3fce8afdbe73b1d6dedd5c426acc5ea321b7b99d3c3469c49f4d68c8c","abstract_canon_sha256":"76901003db8939da119465be9828505913b9d3584e236d964c85793ea1c17ad4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:23.331490Z","signature_b64":"wpeIXbOp5BpWBBLGFUziYIBHUSfOErhspWishVelJQNv3mHyI5X7ggA4mjwtPW/Ln5cBDRLPoL3N47EzcBrWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b56cf6f067315f2a7f337ea1b1f52cdccb558013653b0f0a3323c0dd5d4d74e","last_reissued_at":"2026-07-05T10:51:23.330970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:23.330970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"First-Order Methods for Linearly Constrained Bilevel Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Guy Kornowski, Kai Wang, Suvrit Sra, Swati Padmanabhan, Zhe Zhang","submitted_at":"2024-06-18T16:41:21Z","abstract_excerpt":"Algorithms for bilevel optimization often encounter Hessian computations, which are prohibitive in high dimensions. While recent works offer first-order methods for unconstrained bilevel problems, the constrained setting remains relatively underexplored. We present first-order linearly constrained optimization methods with finite-time hypergradient stationarity guarantees. For linear equality constraints, we attain $\\epsilon$-stationarity in $\\widetilde{O}(\\epsilon^{-2})$ gradient oracle calls, which is nearly-optimal. For linear inequality constraints, we attain $(\\delta,\\epsilon)$-Goldstein "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12771","kind":"arxiv","version":2},"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/2406.12771/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":"2406.12771","created_at":"2026-07-05T10:51:23.331028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12771v2","created_at":"2026-07-05T10:51:23.331028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12771","created_at":"2026-07-05T10:51:23.331028+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNLM63YGOMK7","created_at":"2026-07-05T10:51:23.331028+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNLM63YGOMK7FJ7T","created_at":"2026-07-05T10:51:23.331028+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNLM63YG","created_at":"2026-07-05T10:51:23.331028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16520","citing_title":"Safe Gradient Flow for Bilevel Optimization","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNLM63YGOMK7FJ7TG7VBWH2SZX","json":"https://pith.science/pith/RNLM63YGOMK7FJ7TG7VBWH2SZX.json","graph_json":"https://pith.science/api/pith-number/RNLM63YGOMK7FJ7TG7VBWH2SZX/graph.json","events_json":"https://pith.science/api/pith-number/RNLM63YGOMK7FJ7TG7VBWH2SZX/events.json","paper":"https://pith.science/paper/RNLM63YG"},"agent_actions":{"view_html":"https://pith.science/pith/RNLM63YGOMK7FJ7TG7VBWH2SZX","download_json":"https://pith.science/pith/RNLM63YGOMK7FJ7TG7VBWH2SZX.json","view_paper":"https://pith.science/paper/RNLM63YG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12771&json=true","fetch_graph":"https://pith.science/api/pith-number/RNLM63YGOMK7FJ7TG7VBWH2SZX/graph.json","fetch_events":"https://pith.science/api/pith-number/RNLM63YGOMK7FJ7TG7VBWH2SZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNLM63YGOMK7FJ7TG7VBWH2SZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNLM63YGOMK7FJ7TG7VBWH2SZX/action/storage_attestation","attest_author":"https://pith.science/pith/RNLM63YGOMK7FJ7TG7VBWH2SZX/action/author_attestation","sign_citation":"https://pith.science/pith/RNLM63YGOMK7FJ7TG7VBWH2SZX/action/citation_signature","submit_replication":"https://pith.science/pith/RNLM63YGOMK7FJ7TG7VBWH2SZX/action/replication_record"}},"created_at":"2026-07-05T10:51:23.331028+00:00","updated_at":"2026-07-05T10:51:23.331028+00:00"}