{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NQLKOVMCPSHKML2OODAUWVBRSU","short_pith_number":"pith:NQLKOVMC","schema_version":"1.0","canonical_sha256":"6c16a755827c8ea62f4e70c14b54319529fa25213b97d0e7f7a89702d6215521","source":{"kind":"arxiv","id":"2109.13391","version":2},"attestation_state":"computed","paper":{"title":"Curvature-Aware Derivative-Free Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Bumsu Kim, Daniel McKenzie, HanQin Cai, Wotao Yin","submitted_at":"2021-09-27T23:22:47Z","abstract_excerpt":"The paper discusses derivative-free optimization (DFO), which involves minimizing a function without access to gradients or directional derivatives, only function evaluations. Classical DFO methods, which mimic gradient-based methods, such as Nelder-Mead and direct search have limited scalability for high-dimensional problems. Zeroth-order methods have been gaining popularity due to the demands of large-scale machine learning applications, and the paper focuses on the selection of the step size $\\alpha_k$ in these methods. The proposed approach, called Curvature-Aware Random Search (CARS), use"},"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":"2109.13391","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-09-27T23:22:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e6387108f153bfafeb12b2fe7aa238a6b980974b67a4c011e1a98a609c5c5fcb","abstract_canon_sha256":"c2bc740ca009d015e2ecc546a11b164284ee2abd7707274368cf622478f29b70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:41.810262Z","signature_b64":"NcyxLmfyzCNbYqGe1o+XKAc85yCO5PXPcrRJ0kDm3FK8HSuyG9CWf5eZ3PXLkv9pfsIhuCI1Q/CG1OObhO0CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c16a755827c8ea62f4e70c14b54319529fa25213b97d0e7f7a89702d6215521","last_reissued_at":"2026-07-05T10:49:41.809741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:41.809741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curvature-Aware Derivative-Free Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Bumsu Kim, Daniel McKenzie, HanQin Cai, Wotao Yin","submitted_at":"2021-09-27T23:22:47Z","abstract_excerpt":"The paper discusses derivative-free optimization (DFO), which involves minimizing a function without access to gradients or directional derivatives, only function evaluations. Classical DFO methods, which mimic gradient-based methods, such as Nelder-Mead and direct search have limited scalability for high-dimensional problems. Zeroth-order methods have been gaining popularity due to the demands of large-scale machine learning applications, and the paper focuses on the selection of the step size $\\alpha_k$ in these methods. The proposed approach, called Curvature-Aware Random Search (CARS), use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.13391","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/2109.13391/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":"2109.13391","created_at":"2026-07-05T10:49:41.809794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.13391v2","created_at":"2026-07-05T10:49:41.809794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.13391","created_at":"2026-07-05T10:49:41.809794+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQLKOVMCPSHK","created_at":"2026-07-05T10:49:41.809794+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQLKOVMCPSHKML2O","created_at":"2026-07-05T10:49:41.809794+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQLKOVMC","created_at":"2026-07-05T10:49:41.809794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.01126","citing_title":"Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NQLKOVMCPSHKML2OODAUWVBRSU","json":"https://pith.science/pith/NQLKOVMCPSHKML2OODAUWVBRSU.json","graph_json":"https://pith.science/api/pith-number/NQLKOVMCPSHKML2OODAUWVBRSU/graph.json","events_json":"https://pith.science/api/pith-number/NQLKOVMCPSHKML2OODAUWVBRSU/events.json","paper":"https://pith.science/paper/NQLKOVMC"},"agent_actions":{"view_html":"https://pith.science/pith/NQLKOVMCPSHKML2OODAUWVBRSU","download_json":"https://pith.science/pith/NQLKOVMCPSHKML2OODAUWVBRSU.json","view_paper":"https://pith.science/paper/NQLKOVMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.13391&json=true","fetch_graph":"https://pith.science/api/pith-number/NQLKOVMCPSHKML2OODAUWVBRSU/graph.json","fetch_events":"https://pith.science/api/pith-number/NQLKOVMCPSHKML2OODAUWVBRSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQLKOVMCPSHKML2OODAUWVBRSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQLKOVMCPSHKML2OODAUWVBRSU/action/storage_attestation","attest_author":"https://pith.science/pith/NQLKOVMCPSHKML2OODAUWVBRSU/action/author_attestation","sign_citation":"https://pith.science/pith/NQLKOVMCPSHKML2OODAUWVBRSU/action/citation_signature","submit_replication":"https://pith.science/pith/NQLKOVMCPSHKML2OODAUWVBRSU/action/replication_record"}},"created_at":"2026-07-05T10:49:41.809794+00:00","updated_at":"2026-07-05T10:49:41.809794+00:00"}