{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WFMMI5CJYDXE2ZOUAUAZKXCQ3J","short_pith_number":"pith:WFMMI5CJ","schema_version":"1.0","canonical_sha256":"b158c47449c0ee4d65d40501955c50da5ef28dc1637a59b165968a3f93a46081","source":{"kind":"arxiv","id":"2306.02422","version":4},"attestation_state":"computed","paper":{"title":"A Generalized Alternating Method for Bilevel Learning under the Polyak-{\\L}ojasiewicz Condition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Quan Xiao, Songtao Lu, Tianyi Chen","submitted_at":"2023-06-04T17:54:11Z","abstract_excerpt":"Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning. Recent results have shown that simple alternating (implicit) gradient-based algorithms can match the convergence rate of single-level gradient descent (GD) when addressing bilevel problems with a strongly convex lower-level objective. However, it remains unclear whether this result can be generalized to bilevel problems beyond this basic setting. In this paper, we first introduce a stationary metric for"},"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":"2306.02422","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-06-04T17:54:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7d6fc72550aba3aff994b6674f607d4be5bce8720ef4d2952171e2283c62e226","abstract_canon_sha256":"d0b1c07004719d408c86a7e7fedea6587b9626f464e690563687b3a4f3a6fc0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:39.408781Z","signature_b64":"wVepi+ssv0jzsFmDwfrj4wRMI0NRz3O/IV+X6aC+/1PjYnBNzrMHK9AkQoM6M7WPBORZOfNmKUji+PpWa+TPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b158c47449c0ee4d65d40501955c50da5ef28dc1637a59b165968a3f93a46081","last_reissued_at":"2026-07-05T06:57:39.408242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:39.408242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Generalized Alternating Method for Bilevel Learning under the Polyak-{\\L}ojasiewicz Condition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Quan Xiao, Songtao Lu, Tianyi Chen","submitted_at":"2023-06-04T17:54:11Z","abstract_excerpt":"Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning. Recent results have shown that simple alternating (implicit) gradient-based algorithms can match the convergence rate of single-level gradient descent (GD) when addressing bilevel problems with a strongly convex lower-level objective. However, it remains unclear whether this result can be generalized to bilevel problems beyond this basic setting. In this paper, we first introduce a stationary metric for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02422","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/2306.02422/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":"2306.02422","created_at":"2026-07-05T06:57:39.408308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02422v4","created_at":"2026-07-05T06:57:39.408308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02422","created_at":"2026-07-05T06:57:39.408308+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFMMI5CJYDXE","created_at":"2026-07-05T06:57:39.408308+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFMMI5CJYDXE2ZOU","created_at":"2026-07-05T06:57:39.408308+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFMMI5CJ","created_at":"2026-07-05T06:57:39.408308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06431","citing_title":"Second-Order Bilevel Optimization with Accelerated Convergence Rates","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01621","citing_title":"Bilevel learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13472","citing_title":"Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WFMMI5CJYDXE2ZOUAUAZKXCQ3J","json":"https://pith.science/pith/WFMMI5CJYDXE2ZOUAUAZKXCQ3J.json","graph_json":"https://pith.science/api/pith-number/WFMMI5CJYDXE2ZOUAUAZKXCQ3J/graph.json","events_json":"https://pith.science/api/pith-number/WFMMI5CJYDXE2ZOUAUAZKXCQ3J/events.json","paper":"https://pith.science/paper/WFMMI5CJ"},"agent_actions":{"view_html":"https://pith.science/pith/WFMMI5CJYDXE2ZOUAUAZKXCQ3J","download_json":"https://pith.science/pith/WFMMI5CJYDXE2ZOUAUAZKXCQ3J.json","view_paper":"https://pith.science/paper/WFMMI5CJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02422&json=true","fetch_graph":"https://pith.science/api/pith-number/WFMMI5CJYDXE2ZOUAUAZKXCQ3J/graph.json","fetch_events":"https://pith.science/api/pith-number/WFMMI5CJYDXE2ZOUAUAZKXCQ3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFMMI5CJYDXE2ZOUAUAZKXCQ3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFMMI5CJYDXE2ZOUAUAZKXCQ3J/action/storage_attestation","attest_author":"https://pith.science/pith/WFMMI5CJYDXE2ZOUAUAZKXCQ3J/action/author_attestation","sign_citation":"https://pith.science/pith/WFMMI5CJYDXE2ZOUAUAZKXCQ3J/action/citation_signature","submit_replication":"https://pith.science/pith/WFMMI5CJYDXE2ZOUAUAZKXCQ3J/action/replication_record"}},"created_at":"2026-07-05T06:57:39.408308+00:00","updated_at":"2026-07-05T06:57:39.408308+00:00"}