{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3RVGH667GS4ZL3GLD7T6UILZCP","short_pith_number":"pith:3RVGH667","schema_version":"1.0","canonical_sha256":"dc6a63fbdf34b995eccb1fe7ea217913ef37e05e6b5f2f53842e8c1635ac33ac","source":{"kind":"arxiv","id":"1911.06317","version":4},"attestation_state":"computed","paper":{"title":"Gradientless Descent: High-Dimensional Zeroth-Order Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chansoo Lee, Daniel Golovin, Greg Kochanski, John Karro, Qiuyi Zhang, Xingyou Song","submitted_at":"2019-11-14T18:58:13Z","abstract_excerpt":"Zeroth-order optimization is the process of minimizing an objective $f(x)$, given oracle access to evaluations at adaptively chosen inputs $x$. In this paper, we present two simple yet powerful GradientLess Descent (GLD) algorithms that do not rely on an underlying gradient estimate and are numerically stable. We analyze our algorithm from a novel geometric perspective and present a novel analysis that shows convergence within an $\\epsilon$-ball of the optimum in $O(kQ\\log(n)\\log(R/\\epsilon))$ evaluations, for any monotone transform of a smooth and strongly convex objective with latent dimensi"},"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":"1911.06317","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-14T18:58:13Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"203816e470e0baf02770b32be249604e9e75d707a75820208abc9e81a3172d6b","abstract_canon_sha256":"04c74affd3f49043a15eba6b13f3fe4e07d071495848a06d70682d2ea2a218a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:41.592180Z","signature_b64":"VdT+k/3mFIFiQ/kwZ54cmYv3g0x+YDyP4NNa46XYfTJCVvfbbi1y8w/oV3NoAR9ysG5j7rMeyGV4McfFF9ZVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc6a63fbdf34b995eccb1fe7ea217913ef37e05e6b5f2f53842e8c1635ac33ac","last_reissued_at":"2026-07-05T01:03:41.591683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:41.591683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradientless Descent: High-Dimensional Zeroth-Order Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chansoo Lee, Daniel Golovin, Greg Kochanski, John Karro, Qiuyi Zhang, Xingyou Song","submitted_at":"2019-11-14T18:58:13Z","abstract_excerpt":"Zeroth-order optimization is the process of minimizing an objective $f(x)$, given oracle access to evaluations at adaptively chosen inputs $x$. In this paper, we present two simple yet powerful GradientLess Descent (GLD) algorithms that do not rely on an underlying gradient estimate and are numerically stable. We analyze our algorithm from a novel geometric perspective and present a novel analysis that shows convergence within an $\\epsilon$-ball of the optimum in $O(kQ\\log(n)\\log(R/\\epsilon))$ evaluations, for any monotone transform of a smooth and strongly convex objective with latent dimensi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06317","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/1911.06317/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":"1911.06317","created_at":"2026-07-05T01:03:41.591746+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.06317v4","created_at":"2026-07-05T01:03:41.591746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06317","created_at":"2026-07-05T01:03:41.591746+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RVGH667GS4Z","created_at":"2026-07-05T01:03:41.591746+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RVGH667GS4ZL3GL","created_at":"2026-07-05T01:03:41.591746+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RVGH667","created_at":"2026-07-05T01:03:41.591746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27082","citing_title":"Finding Stationary Points by Comparisons","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RVGH667GS4ZL3GLD7T6UILZCP","json":"https://pith.science/pith/3RVGH667GS4ZL3GLD7T6UILZCP.json","graph_json":"https://pith.science/api/pith-number/3RVGH667GS4ZL3GLD7T6UILZCP/graph.json","events_json":"https://pith.science/api/pith-number/3RVGH667GS4ZL3GLD7T6UILZCP/events.json","paper":"https://pith.science/paper/3RVGH667"},"agent_actions":{"view_html":"https://pith.science/pith/3RVGH667GS4ZL3GLD7T6UILZCP","download_json":"https://pith.science/pith/3RVGH667GS4ZL3GLD7T6UILZCP.json","view_paper":"https://pith.science/paper/3RVGH667","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.06317&json=true","fetch_graph":"https://pith.science/api/pith-number/3RVGH667GS4ZL3GLD7T6UILZCP/graph.json","fetch_events":"https://pith.science/api/pith-number/3RVGH667GS4ZL3GLD7T6UILZCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RVGH667GS4ZL3GLD7T6UILZCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RVGH667GS4ZL3GLD7T6UILZCP/action/storage_attestation","attest_author":"https://pith.science/pith/3RVGH667GS4ZL3GLD7T6UILZCP/action/author_attestation","sign_citation":"https://pith.science/pith/3RVGH667GS4ZL3GLD7T6UILZCP/action/citation_signature","submit_replication":"https://pith.science/pith/3RVGH667GS4ZL3GLD7T6UILZCP/action/replication_record"}},"created_at":"2026-07-05T01:03:41.591746+00:00","updated_at":"2026-07-05T01:03:41.591746+00:00"}