{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BBXMADRZ2JOFHOTAK6H7QESDDF","short_pith_number":"pith:BBXMADRZ","schema_version":"1.0","canonical_sha256":"086ec00e39d25c53ba60578ff81243197cae102a7f644e788bb7546d36b96aad","source":{"kind":"arxiv","id":"2505.02101","version":1},"attestation_state":"computed","paper":{"title":"Efficient Curvature-Aware Hypergradient Approximation for Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Jin Zhang, Junfeng Yang, Wei Yao, Youran Dong","submitted_at":"2025-05-04T13:13:29Z","abstract_excerpt":"Bilevel optimization is a powerful tool for many machine learning problems, such as hyperparameter optimization and meta-learning. Estimating hypergradients (also known as implicit gradients) is crucial for developing gradient-based methods for bilevel optimization. In this work, we propose a computationally efficient technique for incorporating curvature information into the approximation of hypergradients and present a novel algorithmic framework based on the resulting enhanced hypergradient computation. We provide convergence rate guarantees for the proposed framework in both deterministic "},"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":"2505.02101","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-04T13:13:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3e5275408c0794aa4c57584ce5316e8647354b2404ceeea6d69e3d0945db7c4a","abstract_canon_sha256":"ef57cc901d72b831a66175f85611af681722afc5898ed64ee431a1026a1a0269"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:31.990803Z","signature_b64":"ar84cACM2nRmfVoopZLehVKM0WDHfFfQkBxDJ66NF3pDhGoLBS6OzjCYnObqW8qayk8FRswxFzFB/EQwYNnoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"086ec00e39d25c53ba60578ff81243197cae102a7f644e788bb7546d36b96aad","last_reissued_at":"2026-07-05T10:58:31.990294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:31.990294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Curvature-Aware Hypergradient Approximation for Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Jin Zhang, Junfeng Yang, Wei Yao, Youran Dong","submitted_at":"2025-05-04T13:13:29Z","abstract_excerpt":"Bilevel optimization is a powerful tool for many machine learning problems, such as hyperparameter optimization and meta-learning. Estimating hypergradients (also known as implicit gradients) is crucial for developing gradient-based methods for bilevel optimization. In this work, we propose a computationally efficient technique for incorporating curvature information into the approximation of hypergradients and present a novel algorithmic framework based on the resulting enhanced hypergradient computation. We provide convergence rate guarantees for the proposed framework in both deterministic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02101","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/2505.02101/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":"2505.02101","created_at":"2026-07-05T10:58:31.990362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02101v1","created_at":"2026-07-05T10:58:31.990362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02101","created_at":"2026-07-05T10:58:31.990362+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBXMADRZ2JOF","created_at":"2026-07-05T10:58:31.990362+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBXMADRZ2JOFHOTA","created_at":"2026-07-05T10:58:31.990362+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBXMADRZ","created_at":"2026-07-05T10:58:31.990362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06431","citing_title":"Second-Order Bilevel Optimization with Accelerated Convergence Rates","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBXMADRZ2JOFHOTAK6H7QESDDF","json":"https://pith.science/pith/BBXMADRZ2JOFHOTAK6H7QESDDF.json","graph_json":"https://pith.science/api/pith-number/BBXMADRZ2JOFHOTAK6H7QESDDF/graph.json","events_json":"https://pith.science/api/pith-number/BBXMADRZ2JOFHOTAK6H7QESDDF/events.json","paper":"https://pith.science/paper/BBXMADRZ"},"agent_actions":{"view_html":"https://pith.science/pith/BBXMADRZ2JOFHOTAK6H7QESDDF","download_json":"https://pith.science/pith/BBXMADRZ2JOFHOTAK6H7QESDDF.json","view_paper":"https://pith.science/paper/BBXMADRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02101&json=true","fetch_graph":"https://pith.science/api/pith-number/BBXMADRZ2JOFHOTAK6H7QESDDF/graph.json","fetch_events":"https://pith.science/api/pith-number/BBXMADRZ2JOFHOTAK6H7QESDDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBXMADRZ2JOFHOTAK6H7QESDDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBXMADRZ2JOFHOTAK6H7QESDDF/action/storage_attestation","attest_author":"https://pith.science/pith/BBXMADRZ2JOFHOTAK6H7QESDDF/action/author_attestation","sign_citation":"https://pith.science/pith/BBXMADRZ2JOFHOTAK6H7QESDDF/action/citation_signature","submit_replication":"https://pith.science/pith/BBXMADRZ2JOFHOTAK6H7QESDDF/action/replication_record"}},"created_at":"2026-07-05T10:58:31.990362+00:00","updated_at":"2026-07-05T10:58:31.990362+00:00"}