{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EWLA2XUKDRRO7GG7DWNLRI6MB7","short_pith_number":"pith:EWLA2XUK","schema_version":"1.0","canonical_sha256":"25960d5e8a1c62ef98df1d9ab8a3cc0fc5e36ef85be3f76cc62e61c91400aba3","source":{"kind":"arxiv","id":"2406.01992","version":1},"attestation_state":"computed","paper":{"title":"Overcoming Lower-Level Constraints in Bilevel Optimization: A Novel Approach with Regularized Gap Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Haian Yin, Jin Zhang, Shangzhi Zeng, Wei Yao","submitted_at":"2024-06-04T06:22:04Z","abstract_excerpt":"Constrained bilevel optimization tackles nested structures present in constrained learning tasks like constrained meta-learning, adversarial learning, and distributed bilevel optimization. However, existing bilevel optimization methods mostly are typically restricted to specific constraint settings, such as linear lower-level constraints. In this work, we overcome this limitation and develop a new single-loop, Hessian-free constrained bilevel algorithm capable of handling more general lower-level constraints. We achieve this by employing a doubly regularized gap function tailored to the constr"},"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":"2406.01992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-06-04T06:22:04Z","cross_cats_sorted":[],"title_canon_sha256":"51c949a82d0eb68b6695d4a917348d74495e5aadc1041f932a9a62ec5109710d","abstract_canon_sha256":"7efca830e2b46b2938d0df92d18d27682e0f5f58ab22a9debf00a5f5f85ae195"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:13.004885Z","signature_b64":"bXVQMyfQ28UTZGaqSiSK6aAo4YO+D2SR6RHY5plZMYjkW1L2jMXYSFEnnZm7t7nyfvgXAtdHo8fq+7TVCpmsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25960d5e8a1c62ef98df1d9ab8a3cc0fc5e36ef85be3f76cc62e61c91400aba3","last_reissued_at":"2026-07-05T08:27:13.004468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:13.004468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overcoming Lower-Level Constraints in Bilevel Optimization: A Novel Approach with Regularized Gap Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Haian Yin, Jin Zhang, Shangzhi Zeng, Wei Yao","submitted_at":"2024-06-04T06:22:04Z","abstract_excerpt":"Constrained bilevel optimization tackles nested structures present in constrained learning tasks like constrained meta-learning, adversarial learning, and distributed bilevel optimization. However, existing bilevel optimization methods mostly are typically restricted to specific constraint settings, such as linear lower-level constraints. In this work, we overcome this limitation and develop a new single-loop, Hessian-free constrained bilevel algorithm capable of handling more general lower-level constraints. We achieve this by employing a doubly regularized gap function tailored to the constr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01992","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/2406.01992/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":"2406.01992","created_at":"2026-07-05T08:27:13.004523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01992v1","created_at":"2026-07-05T08:27:13.004523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01992","created_at":"2026-07-05T08:27:13.004523+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWLA2XUKDRRO","created_at":"2026-07-05T08:27:13.004523+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWLA2XUKDRRO7GG7","created_at":"2026-07-05T08:27:13.004523+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWLA2XUK","created_at":"2026-07-05T08:27:13.004523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.18929","citing_title":"Alternating Gradient-Type Algorithm for Bilevel Optimization with Inexact Lower-Level Solutions via Moreau Envelope-based Reformulation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09209","citing_title":"Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets","ref_index":175,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20115","citing_title":"On the Stability and Generalization of First-order Bilevel Minimax Optimization","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWLA2XUKDRRO7GG7DWNLRI6MB7","json":"https://pith.science/pith/EWLA2XUKDRRO7GG7DWNLRI6MB7.json","graph_json":"https://pith.science/api/pith-number/EWLA2XUKDRRO7GG7DWNLRI6MB7/graph.json","events_json":"https://pith.science/api/pith-number/EWLA2XUKDRRO7GG7DWNLRI6MB7/events.json","paper":"https://pith.science/paper/EWLA2XUK"},"agent_actions":{"view_html":"https://pith.science/pith/EWLA2XUKDRRO7GG7DWNLRI6MB7","download_json":"https://pith.science/pith/EWLA2XUKDRRO7GG7DWNLRI6MB7.json","view_paper":"https://pith.science/paper/EWLA2XUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01992&json=true","fetch_graph":"https://pith.science/api/pith-number/EWLA2XUKDRRO7GG7DWNLRI6MB7/graph.json","fetch_events":"https://pith.science/api/pith-number/EWLA2XUKDRRO7GG7DWNLRI6MB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWLA2XUKDRRO7GG7DWNLRI6MB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWLA2XUKDRRO7GG7DWNLRI6MB7/action/storage_attestation","attest_author":"https://pith.science/pith/EWLA2XUKDRRO7GG7DWNLRI6MB7/action/author_attestation","sign_citation":"https://pith.science/pith/EWLA2XUKDRRO7GG7DWNLRI6MB7/action/citation_signature","submit_replication":"https://pith.science/pith/EWLA2XUKDRRO7GG7DWNLRI6MB7/action/replication_record"}},"created_at":"2026-07-05T08:27:13.004523+00:00","updated_at":"2026-07-05T08:27:13.004523+00:00"}