{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VIPKXJSJDENQKA5RJ2L5NG7YJY","short_pith_number":"pith:VIPKXJSJ","schema_version":"1.0","canonical_sha256":"aa1eaba649191b0503b14e97d69bf84e08fbcc0754f5c90e09fdf9fae5e0d078","source":{"kind":"arxiv","id":"2110.04974","version":2},"attestation_state":"computed","paper":{"title":"Value-Function-based Sequential Minimization for Bi-level Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Jin Zhang, Risheng Liu, Shangzhi Zeng, Xuan Liu, Yixuan Zhang","submitted_at":"2021-10-11T03:13:39Z","abstract_excerpt":"Gradient-based Bi-Level Optimization (BLO) methods have been widely applied to handle modern learning tasks. However, most existing strategies are theoretically designed based on restrictive assumptions (e.g., convexity of the lower-level sub-problem), and computationally not applicable for high-dimensional tasks. Moreover, there are almost no gradient-based methods able to solve BLO in those challenging scenarios, such as BLO with functional constraints and pessimistic BLO. In this work, by reformulating BLO into approximated single-level problems, we provide a new algorithm, named Bi-level V"},"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":"2110.04974","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T03:13:39Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"152285615f71e54c5d19473f49984efdae1afcfe07c92d515dd6b87ba52326cf","abstract_canon_sha256":"150a7019e703abaa1bbee135ba39e7e7234a15d1330c67571fd8fa964ac415d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:28.819900Z","signature_b64":"FH7CLGNXCkJna3wrm9jWxtlAaLs7Z34B55Rv8K/OON2EUPVlJDq4XkIio6wrTx9P57fm1q2i8Jn/tNGll0WxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa1eaba649191b0503b14e97d69bf84e08fbcc0754f5c90e09fdf9fae5e0d078","last_reissued_at":"2026-07-05T06:07:28.819417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:28.819417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Value-Function-based Sequential Minimization for Bi-level Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Jin Zhang, Risheng Liu, Shangzhi Zeng, Xuan Liu, Yixuan Zhang","submitted_at":"2021-10-11T03:13:39Z","abstract_excerpt":"Gradient-based Bi-Level Optimization (BLO) methods have been widely applied to handle modern learning tasks. However, most existing strategies are theoretically designed based on restrictive assumptions (e.g., convexity of the lower-level sub-problem), and computationally not applicable for high-dimensional tasks. Moreover, there are almost no gradient-based methods able to solve BLO in those challenging scenarios, such as BLO with functional constraints and pessimistic BLO. In this work, by reformulating BLO into approximated single-level problems, we provide a new algorithm, named Bi-level V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04974","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/2110.04974/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":"2110.04974","created_at":"2026-07-05T06:07:28.819476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.04974v2","created_at":"2026-07-05T06:07:28.819476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04974","created_at":"2026-07-05T06:07:28.819476+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIPKXJSJDENQ","created_at":"2026-07-05T06:07:28.819476+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIPKXJSJDENQKA5R","created_at":"2026-07-05T06:07:28.819476+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIPKXJSJ","created_at":"2026-07-05T06:07:28.819476+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/VIPKXJSJDENQKA5RJ2L5NG7YJY","json":"https://pith.science/pith/VIPKXJSJDENQKA5RJ2L5NG7YJY.json","graph_json":"https://pith.science/api/pith-number/VIPKXJSJDENQKA5RJ2L5NG7YJY/graph.json","events_json":"https://pith.science/api/pith-number/VIPKXJSJDENQKA5RJ2L5NG7YJY/events.json","paper":"https://pith.science/paper/VIPKXJSJ"},"agent_actions":{"view_html":"https://pith.science/pith/VIPKXJSJDENQKA5RJ2L5NG7YJY","download_json":"https://pith.science/pith/VIPKXJSJDENQKA5RJ2L5NG7YJY.json","view_paper":"https://pith.science/paper/VIPKXJSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.04974&json=true","fetch_graph":"https://pith.science/api/pith-number/VIPKXJSJDENQKA5RJ2L5NG7YJY/graph.json","fetch_events":"https://pith.science/api/pith-number/VIPKXJSJDENQKA5RJ2L5NG7YJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIPKXJSJDENQKA5RJ2L5NG7YJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIPKXJSJDENQKA5RJ2L5NG7YJY/action/storage_attestation","attest_author":"https://pith.science/pith/VIPKXJSJDENQKA5RJ2L5NG7YJY/action/author_attestation","sign_citation":"https://pith.science/pith/VIPKXJSJDENQKA5RJ2L5NG7YJY/action/citation_signature","submit_replication":"https://pith.science/pith/VIPKXJSJDENQKA5RJ2L5NG7YJY/action/replication_record"}},"created_at":"2026-07-05T06:07:28.819476+00:00","updated_at":"2026-07-05T06:07:28.819476+00:00"}