{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RCE5YPHZMHLMPWCV6KSVI7WK56","short_pith_number":"pith:RCE5YPHZ","schema_version":"1.0","canonical_sha256":"8889dc3cf961d6c7d855f2a5547ecaef92bd701a3b241c8fc7f10fc6947a9f86","source":{"kind":"arxiv","id":"2207.11719","version":4},"attestation_state":"computed","paper":{"title":"Gradient-based Bi-level Optimization for Deep Learning: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Can Chen, Chen Ma, Xi Chen, Xue Liu, Zixuan Liu","submitted_at":"2022-07-24T11:23:31Z","abstract_excerpt":"Bi-level optimization, especially the gradient-based category, has been widely used in the deep learning community including hyperparameter optimization and meta-knowledge extraction. Bi-level optimization embeds one problem within another and the gradient-based category solves the outer-level task by computing the hypergradient, which is much more efficient than classical methods such as the evolutionary algorithm. In this survey, we first give a formal definition of the gradient-based bi-level optimization. Next, we delineate criteria to determine if a research problem is apt for bi-level op"},"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":"2207.11719","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-24T11:23:31Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"603d0851b9403119f2be4d571f798a779b77abc81cfd19097056a78256779e7c","abstract_canon_sha256":"ceaac6d4378d1f586de71dbdb4841acc0d6cca5de78cf8afc30a13a91e7f1d34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:55.140970Z","signature_b64":"4XlRolVjfWTo7q1e9jZAopy5RPsfuJFWmNQrx2L6L7PTdeTw6HgljUsw3PrqChN0eX5P7JBD+xX1zL77nJsoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8889dc3cf961d6c7d855f2a5547ecaef92bd701a3b241c8fc7f10fc6947a9f86","last_reissued_at":"2026-07-05T06:28:55.140529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:55.140529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient-based Bi-level Optimization for Deep Learning: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Can Chen, Chen Ma, Xi Chen, Xue Liu, Zixuan Liu","submitted_at":"2022-07-24T11:23:31Z","abstract_excerpt":"Bi-level optimization, especially the gradient-based category, has been widely used in the deep learning community including hyperparameter optimization and meta-knowledge extraction. Bi-level optimization embeds one problem within another and the gradient-based category solves the outer-level task by computing the hypergradient, which is much more efficient than classical methods such as the evolutionary algorithm. In this survey, we first give a formal definition of the gradient-based bi-level optimization. Next, we delineate criteria to determine if a research problem is apt for bi-level op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.11719","kind":"arxiv","version":4},"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/2207.11719/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":"2207.11719","created_at":"2026-07-05T06:28:55.140575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.11719v4","created_at":"2026-07-05T06:28:55.140575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.11719","created_at":"2026-07-05T06:28:55.140575+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCE5YPHZMHLM","created_at":"2026-07-05T06:28:55.140575+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCE5YPHZMHLMPWCV","created_at":"2026-07-05T06:28:55.140575+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCE5YPHZ","created_at":"2026-07-05T06:28:55.140575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00571","citing_title":"On the Difficulty of Learning a Meta-network for Training Data Selection","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12718","citing_title":"CHAL: Council of Hierarchical Agentic Language","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCE5YPHZMHLMPWCV6KSVI7WK56","json":"https://pith.science/pith/RCE5YPHZMHLMPWCV6KSVI7WK56.json","graph_json":"https://pith.science/api/pith-number/RCE5YPHZMHLMPWCV6KSVI7WK56/graph.json","events_json":"https://pith.science/api/pith-number/RCE5YPHZMHLMPWCV6KSVI7WK56/events.json","paper":"https://pith.science/paper/RCE5YPHZ"},"agent_actions":{"view_html":"https://pith.science/pith/RCE5YPHZMHLMPWCV6KSVI7WK56","download_json":"https://pith.science/pith/RCE5YPHZMHLMPWCV6KSVI7WK56.json","view_paper":"https://pith.science/paper/RCE5YPHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.11719&json=true","fetch_graph":"https://pith.science/api/pith-number/RCE5YPHZMHLMPWCV6KSVI7WK56/graph.json","fetch_events":"https://pith.science/api/pith-number/RCE5YPHZMHLMPWCV6KSVI7WK56/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCE5YPHZMHLMPWCV6KSVI7WK56/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCE5YPHZMHLMPWCV6KSVI7WK56/action/storage_attestation","attest_author":"https://pith.science/pith/RCE5YPHZMHLMPWCV6KSVI7WK56/action/author_attestation","sign_citation":"https://pith.science/pith/RCE5YPHZMHLMPWCV6KSVI7WK56/action/citation_signature","submit_replication":"https://pith.science/pith/RCE5YPHZMHLMPWCV6KSVI7WK56/action/replication_record"}},"created_at":"2026-07-05T06:28:55.140575+00:00","updated_at":"2026-07-05T06:28:55.140575+00:00"}