{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VF5R5RQNMDD6PRTPZA7UGVJX76","short_pith_number":"pith:VF5R5RQN","schema_version":"1.0","canonical_sha256":"a97b1ec60d60c7e7c66fc83f435537ffbc477a8ebf93e01cb746aa288d8cd63a","source":{"kind":"arxiv","id":"2306.11211","version":1},"attestation_state":"computed","paper":{"title":"A New Simple Stochastic Gradient Descent Type Algorithm With Lower Computational Complexity for Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Haimei Huo, Risheng Liu, Zhixun Su","submitted_at":"2023-06-20T00:32:13Z","abstract_excerpt":"Bilevel optimization has been widely used in many machine learning applications such as hyperparameter optimization and meta learning. Recently, many simple stochastic gradient descent(SGD) type algorithms(without using momentum and variance techniques) have been proposed to solve the bilevel optimization problems. However, all the existing simple SGD type algorithms estimate the hypergradient via stochastic estimation of Neumann series. In the paper, we propose to estimate the hypergradient via SGD-based Estimation(i.e., solving the linear system with SGD). By using warm start initialization "},"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":"2306.11211","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-06-20T00:32:13Z","cross_cats_sorted":[],"title_canon_sha256":"2f63d4747f1239f1ba8180848a4af162c31b5357294fe0b50583efc7f3ef1521","abstract_canon_sha256":"a9317eeb15d988448c3b0fa6fdcff31b00fa0f36e7923697a1e24c3ed93a814d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:17.282171Z","signature_b64":"LVj27E051ExogNBnRz+wbZ+MeYs5HVF1R1XBmZiiBf0Nf3JPHxt/kCeqawxjyHR7xJxEyhYXdoKz9XRCOozaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a97b1ec60d60c7e7c66fc83f435537ffbc477a8ebf93e01cb746aa288d8cd63a","last_reissued_at":"2026-07-05T06:22:17.281739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:17.281739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A New Simple Stochastic Gradient Descent Type Algorithm With Lower Computational Complexity for Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Haimei Huo, Risheng Liu, Zhixun Su","submitted_at":"2023-06-20T00:32:13Z","abstract_excerpt":"Bilevel optimization has been widely used in many machine learning applications such as hyperparameter optimization and meta learning. Recently, many simple stochastic gradient descent(SGD) type algorithms(without using momentum and variance techniques) have been proposed to solve the bilevel optimization problems. However, all the existing simple SGD type algorithms estimate the hypergradient via stochastic estimation of Neumann series. In the paper, we propose to estimate the hypergradient via SGD-based Estimation(i.e., solving the linear system with SGD). By using warm start initialization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11211","kind":"arxiv","version":1},"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/2306.11211/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":"2306.11211","created_at":"2026-07-05T06:22:17.281797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11211v1","created_at":"2026-07-05T06:22:17.281797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11211","created_at":"2026-07-05T06:22:17.281797+00:00"},{"alias_kind":"pith_short_12","alias_value":"VF5R5RQNMDD6","created_at":"2026-07-05T06:22:17.281797+00:00"},{"alias_kind":"pith_short_16","alias_value":"VF5R5RQNMDD6PRTP","created_at":"2026-07-05T06:22:17.281797+00:00"},{"alias_kind":"pith_short_8","alias_value":"VF5R5RQN","created_at":"2026-07-05T06:22:17.281797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06431","citing_title":"Second-Order Bilevel Optimization with Accelerated Convergence Rates","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VF5R5RQNMDD6PRTPZA7UGVJX76","json":"https://pith.science/pith/VF5R5RQNMDD6PRTPZA7UGVJX76.json","graph_json":"https://pith.science/api/pith-number/VF5R5RQNMDD6PRTPZA7UGVJX76/graph.json","events_json":"https://pith.science/api/pith-number/VF5R5RQNMDD6PRTPZA7UGVJX76/events.json","paper":"https://pith.science/paper/VF5R5RQN"},"agent_actions":{"view_html":"https://pith.science/pith/VF5R5RQNMDD6PRTPZA7UGVJX76","download_json":"https://pith.science/pith/VF5R5RQNMDD6PRTPZA7UGVJX76.json","view_paper":"https://pith.science/paper/VF5R5RQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11211&json=true","fetch_graph":"https://pith.science/api/pith-number/VF5R5RQNMDD6PRTPZA7UGVJX76/graph.json","fetch_events":"https://pith.science/api/pith-number/VF5R5RQNMDD6PRTPZA7UGVJX76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VF5R5RQNMDD6PRTPZA7UGVJX76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VF5R5RQNMDD6PRTPZA7UGVJX76/action/storage_attestation","attest_author":"https://pith.science/pith/VF5R5RQNMDD6PRTPZA7UGVJX76/action/author_attestation","sign_citation":"https://pith.science/pith/VF5R5RQNMDD6PRTPZA7UGVJX76/action/citation_signature","submit_replication":"https://pith.science/pith/VF5R5RQNMDD6PRTPZA7UGVJX76/action/replication_record"}},"created_at":"2026-07-05T06:22:17.281797+00:00","updated_at":"2026-07-05T06:22:17.281797+00:00"}