{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6E3QEDIEEL7U5MHP3E7TLU7VOC","short_pith_number":"pith:6E3QEDIE","schema_version":"1.0","canonical_sha256":"f137020d0422ff4eb0efd93f35d3f5709baffc3e3c31e67041e23d3ab503e79b","source":{"kind":"arxiv","id":"2406.14095","version":2},"attestation_state":"computed","paper":{"title":"Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haonan Wang, Jonathan Scarlett, Kenji Kawaguchi, Qianli Shen, Xiang Li, Yang Zhang, Yezhen Wang, Zhanxing Zhu, Zhouhao Yang","submitted_at":"2024-06-20T08:21:52Z","abstract_excerpt":"Bi-level optimization (BO) has become a fundamental mathematical framework for addressing hierarchical machine learning problems. As deep learning models continue to grow in size, the demand for scalable bi-level optimization solutions has become increasingly critical. Traditional gradient-based bi-level optimization algorithms, due to their inherent characteristics, are ill-suited to meet the demands of large-scale applications. In this paper, we introduce $\\textbf{F}$orward $\\textbf{G}$radient $\\textbf{U}$nrolling with $\\textbf{F}$orward $\\textbf{F}$radient, abbreviated as $(\\textbf{FG})^2\\t"},"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":"2406.14095","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T08:21:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6b9fcaea762609415fab41be74e9a51178cab17de0ad3087c6696f18d20703fa","abstract_canon_sha256":"f28d2601467ea814c2b179495d83a23547b883eb6b2748f2a78e58429c4a05be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:41.891854Z","signature_b64":"Pp2h+YeQgnApHR7Rp/114NJyCHDgWqkcJ0YMKThqgT2QCPlNCutSyj40HtyDzY5XMITiFSHnKdX9QG2M5FdzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f137020d0422ff4eb0efd93f35d3f5709baffc3e3c31e67041e23d3ab503e79b","last_reissued_at":"2026-07-05T09:53:41.891453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:41.891453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haonan Wang, Jonathan Scarlett, Kenji Kawaguchi, Qianli Shen, Xiang Li, Yang Zhang, Yezhen Wang, Zhanxing Zhu, Zhouhao Yang","submitted_at":"2024-06-20T08:21:52Z","abstract_excerpt":"Bi-level optimization (BO) has become a fundamental mathematical framework for addressing hierarchical machine learning problems. As deep learning models continue to grow in size, the demand for scalable bi-level optimization solutions has become increasingly critical. Traditional gradient-based bi-level optimization algorithms, due to their inherent characteristics, are ill-suited to meet the demands of large-scale applications. In this paper, we introduce $\\textbf{F}$orward $\\textbf{G}$radient $\\textbf{U}$nrolling with $\\textbf{F}$orward $\\textbf{F}$radient, abbreviated as $(\\textbf{FG})^2\\t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14095","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/2406.14095/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":"2406.14095","created_at":"2026-07-05T09:53:41.891510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14095v2","created_at":"2026-07-05T09:53:41.891510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14095","created_at":"2026-07-05T09:53:41.891510+00:00"},{"alias_kind":"pith_short_12","alias_value":"6E3QEDIEEL7U","created_at":"2026-07-05T09:53:41.891510+00:00"},{"alias_kind":"pith_short_16","alias_value":"6E3QEDIEEL7U5MHP","created_at":"2026-07-05T09:53:41.891510+00:00"},{"alias_kind":"pith_short_8","alias_value":"6E3QEDIE","created_at":"2026-07-05T09:53:41.891510+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/6E3QEDIEEL7U5MHP3E7TLU7VOC","json":"https://pith.science/pith/6E3QEDIEEL7U5MHP3E7TLU7VOC.json","graph_json":"https://pith.science/api/pith-number/6E3QEDIEEL7U5MHP3E7TLU7VOC/graph.json","events_json":"https://pith.science/api/pith-number/6E3QEDIEEL7U5MHP3E7TLU7VOC/events.json","paper":"https://pith.science/paper/6E3QEDIE"},"agent_actions":{"view_html":"https://pith.science/pith/6E3QEDIEEL7U5MHP3E7TLU7VOC","download_json":"https://pith.science/pith/6E3QEDIEEL7U5MHP3E7TLU7VOC.json","view_paper":"https://pith.science/paper/6E3QEDIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14095&json=true","fetch_graph":"https://pith.science/api/pith-number/6E3QEDIEEL7U5MHP3E7TLU7VOC/graph.json","fetch_events":"https://pith.science/api/pith-number/6E3QEDIEEL7U5MHP3E7TLU7VOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6E3QEDIEEL7U5MHP3E7TLU7VOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6E3QEDIEEL7U5MHP3E7TLU7VOC/action/storage_attestation","attest_author":"https://pith.science/pith/6E3QEDIEEL7U5MHP3E7TLU7VOC/action/author_attestation","sign_citation":"https://pith.science/pith/6E3QEDIEEL7U5MHP3E7TLU7VOC/action/citation_signature","submit_replication":"https://pith.science/pith/6E3QEDIEEL7U5MHP3E7TLU7VOC/action/replication_record"}},"created_at":"2026-07-05T09:53:41.891510+00:00","updated_at":"2026-07-05T09:53:41.891510+00:00"}