{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H2MBD76CC2QMTYFKWQQ3GPY6R4","short_pith_number":"pith:H2MBD76C","schema_version":"1.0","canonical_sha256":"3e9811ffc216a0c9e0aab421b33f1e8f261846ef2f2196d1f969d56d5f6ece50","source":{"kind":"arxiv","id":"2211.07096","version":2},"attestation_state":"computed","paper":{"title":"Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Shen, Quan Xiao, Tianyi Chen, Wotao Yin","submitted_at":"2022-11-14T03:47:43Z","abstract_excerpt":"Stochastic bilevel optimization, which captures the inherent nested structure of machine learning problems, is gaining popularity in many recent applications. Existing works on bilevel optimization mostly consider either unconstrained problems or constrained upper-level problems. This paper considers the stochastic bilevel optimization problems with equality constraints both in the upper and lower levels. By leveraging the special structure of the equality constraints problem, the paper first presents an alternating implicit projected SGD approach and establishes the $\\tilde{\\cal O}(\\epsilon^{"},"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":"2211.07096","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-14T03:47:43Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"32a70d3d5c5b7cf19a4b5985a7e3b17a62d2b694ee327441f4f25eca6811c916","abstract_canon_sha256":"1147f05cb6adefe4b6e33b9805329165580b128c964be69531f658024a0355c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:50.983192Z","signature_b64":"+tLCBspUP+RjpIwg3oj4J9PQUGCQW1er6MDhn9FOEv9+ft51t9/9SY0wdIAy/605zWA68EkzEZvXHWO/9G8UBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e9811ffc216a0c9e0aab421b33f1e8f261846ef2f2196d1f969d56d5f6ece50","last_reissued_at":"2026-07-05T05:40:50.982754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:50.982754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Shen, Quan Xiao, Tianyi Chen, Wotao Yin","submitted_at":"2022-11-14T03:47:43Z","abstract_excerpt":"Stochastic bilevel optimization, which captures the inherent nested structure of machine learning problems, is gaining popularity in many recent applications. Existing works on bilevel optimization mostly consider either unconstrained problems or constrained upper-level problems. This paper considers the stochastic bilevel optimization problems with equality constraints both in the upper and lower levels. By leveraging the special structure of the equality constraints problem, the paper first presents an alternating implicit projected SGD approach and establishes the $\\tilde{\\cal O}(\\epsilon^{"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07096","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/2211.07096/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":"2211.07096","created_at":"2026-07-05T05:40:50.982811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.07096v2","created_at":"2026-07-05T05:40:50.982811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07096","created_at":"2026-07-05T05:40:50.982811+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2MBD76CC2QM","created_at":"2026-07-05T05:40:50.982811+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2MBD76CC2QMTYFK","created_at":"2026-07-05T05:40:50.982811+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2MBD76C","created_at":"2026-07-05T05:40:50.982811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08006","citing_title":"Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H2MBD76CC2QMTYFKWQQ3GPY6R4","json":"https://pith.science/pith/H2MBD76CC2QMTYFKWQQ3GPY6R4.json","graph_json":"https://pith.science/api/pith-number/H2MBD76CC2QMTYFKWQQ3GPY6R4/graph.json","events_json":"https://pith.science/api/pith-number/H2MBD76CC2QMTYFKWQQ3GPY6R4/events.json","paper":"https://pith.science/paper/H2MBD76C"},"agent_actions":{"view_html":"https://pith.science/pith/H2MBD76CC2QMTYFKWQQ3GPY6R4","download_json":"https://pith.science/pith/H2MBD76CC2QMTYFKWQQ3GPY6R4.json","view_paper":"https://pith.science/paper/H2MBD76C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.07096&json=true","fetch_graph":"https://pith.science/api/pith-number/H2MBD76CC2QMTYFKWQQ3GPY6R4/graph.json","fetch_events":"https://pith.science/api/pith-number/H2MBD76CC2QMTYFKWQQ3GPY6R4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2MBD76CC2QMTYFKWQQ3GPY6R4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2MBD76CC2QMTYFKWQQ3GPY6R4/action/storage_attestation","attest_author":"https://pith.science/pith/H2MBD76CC2QMTYFKWQQ3GPY6R4/action/author_attestation","sign_citation":"https://pith.science/pith/H2MBD76CC2QMTYFKWQQ3GPY6R4/action/citation_signature","submit_replication":"https://pith.science/pith/H2MBD76CC2QMTYFKWQQ3GPY6R4/action/replication_record"}},"created_at":"2026-07-05T05:40:50.982811+00:00","updated_at":"2026-07-05T05:40:50.982811+00:00"}