{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H256QC4ST5NXGS2CW4BIULRODZ","short_pith_number":"pith:H256QC4S","schema_version":"1.0","canonical_sha256":"3ebbe80b929f5b734b42b7028a2e2e1e5e3f0671e20daadcb050a4e23adbb329","source":{"kind":"arxiv","id":"2504.17215","version":1},"attestation_state":"computed","paper":{"title":"Perturbed Gradient Descent via Convex Quadratic Approximation for Nonconvex Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Erfan Yazdandoost Hamedani, Mahyar Fazlyab, Nazanin Abolfazli, Sina Sharifi","submitted_at":"2025-04-24T03:07:23Z","abstract_excerpt":"Bilevel optimization is a fundamental tool in hierarchical decision-making and has been widely applied to machine learning tasks such as hyperparameter tuning, meta-learning, and continual learning. While significant progress has been made in bilevel optimization, existing methods predominantly focus on the {nonconvex-strongly convex, or the} nonconvex-PL settings, leaving the more general nonconvex-nonconvex framework underexplored. In this paper, we address this gap by developing an efficient gradient-based method inspired by the recently proposed Relaxed Gradient Flow (RXGF) framework with "},"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":"2504.17215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-04-24T03:07:23Z","cross_cats_sorted":[],"title_canon_sha256":"a2b290623a4243ed897ed0fac5ea101fbf0c5e50988491a46f82be9092bba109","abstract_canon_sha256":"d344f3a48e8fb6a7e9fbbb48960e6f4400b8faedf1883f06daec398b2eaf0287"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:24.366651Z","signature_b64":"SDg2eirXzoEDMZIGnsbVo06ptA4UzqmwWCDBLBGlRe7O7ToWfGiXupGxdlsc8u+epqO4/Egd9SlWHf4qFKEhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ebbe80b929f5b734b42b7028a2e2e1e5e3f0671e20daadcb050a4e23adbb329","last_reissued_at":"2026-07-05T10:53:24.366204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:24.366204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perturbed Gradient Descent via Convex Quadratic Approximation for Nonconvex Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Erfan Yazdandoost Hamedani, Mahyar Fazlyab, Nazanin Abolfazli, Sina Sharifi","submitted_at":"2025-04-24T03:07:23Z","abstract_excerpt":"Bilevel optimization is a fundamental tool in hierarchical decision-making and has been widely applied to machine learning tasks such as hyperparameter tuning, meta-learning, and continual learning. While significant progress has been made in bilevel optimization, existing methods predominantly focus on the {nonconvex-strongly convex, or the} nonconvex-PL settings, leaving the more general nonconvex-nonconvex framework underexplored. In this paper, we address this gap by developing an efficient gradient-based method inspired by the recently proposed Relaxed Gradient Flow (RXGF) framework with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17215","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/2504.17215/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":"2504.17215","created_at":"2026-07-05T10:53:24.366262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.17215v1","created_at":"2026-07-05T10:53:24.366262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17215","created_at":"2026-07-05T10:53:24.366262+00:00"},{"alias_kind":"pith_short_12","alias_value":"H256QC4ST5NX","created_at":"2026-07-05T10:53:24.366262+00:00"},{"alias_kind":"pith_short_16","alias_value":"H256QC4ST5NXGS2C","created_at":"2026-07-05T10:53:24.366262+00:00"},{"alias_kind":"pith_short_8","alias_value":"H256QC4S","created_at":"2026-07-05T10:53:24.366262+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/H256QC4ST5NXGS2CW4BIULRODZ","json":"https://pith.science/pith/H256QC4ST5NXGS2CW4BIULRODZ.json","graph_json":"https://pith.science/api/pith-number/H256QC4ST5NXGS2CW4BIULRODZ/graph.json","events_json":"https://pith.science/api/pith-number/H256QC4ST5NXGS2CW4BIULRODZ/events.json","paper":"https://pith.science/paper/H256QC4S"},"agent_actions":{"view_html":"https://pith.science/pith/H256QC4ST5NXGS2CW4BIULRODZ","download_json":"https://pith.science/pith/H256QC4ST5NXGS2CW4BIULRODZ.json","view_paper":"https://pith.science/paper/H256QC4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.17215&json=true","fetch_graph":"https://pith.science/api/pith-number/H256QC4ST5NXGS2CW4BIULRODZ/graph.json","fetch_events":"https://pith.science/api/pith-number/H256QC4ST5NXGS2CW4BIULRODZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H256QC4ST5NXGS2CW4BIULRODZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H256QC4ST5NXGS2CW4BIULRODZ/action/storage_attestation","attest_author":"https://pith.science/pith/H256QC4ST5NXGS2CW4BIULRODZ/action/author_attestation","sign_citation":"https://pith.science/pith/H256QC4ST5NXGS2CW4BIULRODZ/action/citation_signature","submit_replication":"https://pith.science/pith/H256QC4ST5NXGS2CW4BIULRODZ/action/replication_record"}},"created_at":"2026-07-05T10:53:24.366262+00:00","updated_at":"2026-07-05T10:53:24.366262+00:00"}