{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3EZ7ZM47P7UHHRAYQJCCIJ4WRO","short_pith_number":"pith:3EZ7ZM47","schema_version":"1.0","canonical_sha256":"d933fcb39f7fe873c41882442427968b8b549c003ac666ce1096a9e1b0e8d441","source":{"kind":"arxiv","id":"2010.07962","version":3},"attestation_state":"computed","paper":{"title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junjie Yang, Kaiyi Ji, Yingbin Liang","submitted_at":"2020-10-15T18:09:48Z","abstract_excerpt":"Bilevel optimization has arisen as a powerful tool for many machine learning problems such as meta-learning, hyperparameter optimization, and reinforcement learning. In this paper, we investigate the nonconvex-strongly-convex bilevel optimization problem. For deterministic bilevel optimization, we provide a comprehensive convergence rate analysis for two popular algorithms respectively based on approximate implicit differentiation (AID) and iterative differentiation (ITD). For the AID-based method, we orderwisely improve the previous convergence rate analysis due to a more practical parameter "},"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":"2010.07962","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-15T18:09:48Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"3dffe43fc8d98b1c04e931389bd2b0bd00328bc27ce71fba28259cb7d574cdad","abstract_canon_sha256":"2f4550a060abf91be15da2279a53f5a3db1fd0b9231f3912b9ba70eb3f218ab4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:16.173723Z","signature_b64":"NTHdTu53EICs2vMIrT5/kJ+CUJERGJZjTbe9qjGQul5fqyZY7n97rLEiuzKyRzBJg7KpkunAyaEebnM3AVfGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d933fcb39f7fe873c41882442427968b8b549c003ac666ce1096a9e1b0e8d441","last_reissued_at":"2026-07-05T03:09:16.173387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:16.173387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junjie Yang, Kaiyi Ji, Yingbin Liang","submitted_at":"2020-10-15T18:09:48Z","abstract_excerpt":"Bilevel optimization has arisen as a powerful tool for many machine learning problems such as meta-learning, hyperparameter optimization, and reinforcement learning. In this paper, we investigate the nonconvex-strongly-convex bilevel optimization problem. For deterministic bilevel optimization, we provide a comprehensive convergence rate analysis for two popular algorithms respectively based on approximate implicit differentiation (AID) and iterative differentiation (ITD). For the AID-based method, we orderwisely improve the previous convergence rate analysis due to a more practical parameter "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07962","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/2010.07962/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":"2010.07962","created_at":"2026-07-05T03:09:16.173443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.07962v3","created_at":"2026-07-05T03:09:16.173443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07962","created_at":"2026-07-05T03:09:16.173443+00:00"},{"alias_kind":"pith_short_12","alias_value":"3EZ7ZM47P7UH","created_at":"2026-07-05T03:09:16.173443+00:00"},{"alias_kind":"pith_short_16","alias_value":"3EZ7ZM47P7UHHRAY","created_at":"2026-07-05T03:09:16.173443+00:00"},{"alias_kind":"pith_short_8","alias_value":"3EZ7ZM47","created_at":"2026-07-05T03:09:16.173443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12693","citing_title":"IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3EZ7ZM47P7UHHRAYQJCCIJ4WRO","json":"https://pith.science/pith/3EZ7ZM47P7UHHRAYQJCCIJ4WRO.json","graph_json":"https://pith.science/api/pith-number/3EZ7ZM47P7UHHRAYQJCCIJ4WRO/graph.json","events_json":"https://pith.science/api/pith-number/3EZ7ZM47P7UHHRAYQJCCIJ4WRO/events.json","paper":"https://pith.science/paper/3EZ7ZM47"},"agent_actions":{"view_html":"https://pith.science/pith/3EZ7ZM47P7UHHRAYQJCCIJ4WRO","download_json":"https://pith.science/pith/3EZ7ZM47P7UHHRAYQJCCIJ4WRO.json","view_paper":"https://pith.science/paper/3EZ7ZM47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.07962&json=true","fetch_graph":"https://pith.science/api/pith-number/3EZ7ZM47P7UHHRAYQJCCIJ4WRO/graph.json","fetch_events":"https://pith.science/api/pith-number/3EZ7ZM47P7UHHRAYQJCCIJ4WRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3EZ7ZM47P7UHHRAYQJCCIJ4WRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3EZ7ZM47P7UHHRAYQJCCIJ4WRO/action/storage_attestation","attest_author":"https://pith.science/pith/3EZ7ZM47P7UHHRAYQJCCIJ4WRO/action/author_attestation","sign_citation":"https://pith.science/pith/3EZ7ZM47P7UHHRAYQJCCIJ4WRO/action/citation_signature","submit_replication":"https://pith.science/pith/3EZ7ZM47P7UHHRAYQJCCIJ4WRO/action/replication_record"}},"created_at":"2026-07-05T03:09:16.173443+00:00","updated_at":"2026-07-05T03:09:16.173443+00:00"}