{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DUOH24XMGTITU5NFM33QW7AK3J","short_pith_number":"pith:DUOH24XM","schema_version":"1.0","canonical_sha256":"1d1c7d72ec34d13a75a566f70b7c0ada7b8501fb02f49b06b80e5f0ba3287696","source":{"kind":"arxiv","id":"2006.07862","version":4},"attestation_state":"computed","paper":{"title":"Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre B. Tsybakov, Arya Akhavan, Massimiliano Pontil","submitted_at":"2020-06-14T10:42:23Z","abstract_excerpt":"We study the problem of zero-order optimization of a strongly convex function. The goal is to find the minimizer of the function by a sequential exploration of its values, under measurement noise. We study the impact of higher order smoothness properties of the function on the optimization error and on the cumulative regret. To solve this problem we consider a randomized approximation of the projected gradient descent algorithm. The gradient is estimated by a randomized procedure involving two function evaluations and a smoothing kernel. We derive upper bounds for this algorithm both in the co"},"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":"2006.07862","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T10:42:23Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"2f58ed63b73e2db626730436ae992998daa385047c2d5ba41f8b99e3c8513fd7","abstract_canon_sha256":"3e023244f7dfc849bc565e29fc97a60f0e91ba569b220071876d4f25d318c930"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:09.396482Z","signature_b64":"D+s7JzyeuzK9XoCQlMI3KA6vzv1QNhER6Hw/s6RqSglaB+n9qLmT//cRCnK2u4V8zjPu7zsMGLOuIF0yFGDADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d1c7d72ec34d13a75a566f70b7c0ada7b8501fb02f49b06b80e5f0ba3287696","last_reissued_at":"2026-07-05T05:19:09.396080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:09.396080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre B. Tsybakov, Arya Akhavan, Massimiliano Pontil","submitted_at":"2020-06-14T10:42:23Z","abstract_excerpt":"We study the problem of zero-order optimization of a strongly convex function. The goal is to find the minimizer of the function by a sequential exploration of its values, under measurement noise. We study the impact of higher order smoothness properties of the function on the optimization error and on the cumulative regret. To solve this problem we consider a randomized approximation of the projected gradient descent algorithm. The gradient is estimated by a randomized procedure involving two function evaluations and a smoothing kernel. We derive upper bounds for this algorithm both in the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07862","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/2006.07862/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":"2006.07862","created_at":"2026-07-05T05:19:09.396136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07862v4","created_at":"2026-07-05T05:19:09.396136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07862","created_at":"2026-07-05T05:19:09.396136+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUOH24XMGTIT","created_at":"2026-07-05T05:19:09.396136+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUOH24XMGTITU5NF","created_at":"2026-07-05T05:19:09.396136+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUOH24XM","created_at":"2026-07-05T05:19:09.396136+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04566","citing_title":"Optimal minimization of an unknown function in a nonparametric multivariate regression model thanks to a dimension reduction approach","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUOH24XMGTITU5NFM33QW7AK3J","json":"https://pith.science/pith/DUOH24XMGTITU5NFM33QW7AK3J.json","graph_json":"https://pith.science/api/pith-number/DUOH24XMGTITU5NFM33QW7AK3J/graph.json","events_json":"https://pith.science/api/pith-number/DUOH24XMGTITU5NFM33QW7AK3J/events.json","paper":"https://pith.science/paper/DUOH24XM"},"agent_actions":{"view_html":"https://pith.science/pith/DUOH24XMGTITU5NFM33QW7AK3J","download_json":"https://pith.science/pith/DUOH24XMGTITU5NFM33QW7AK3J.json","view_paper":"https://pith.science/paper/DUOH24XM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07862&json=true","fetch_graph":"https://pith.science/api/pith-number/DUOH24XMGTITU5NFM33QW7AK3J/graph.json","fetch_events":"https://pith.science/api/pith-number/DUOH24XMGTITU5NFM33QW7AK3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUOH24XMGTITU5NFM33QW7AK3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUOH24XMGTITU5NFM33QW7AK3J/action/storage_attestation","attest_author":"https://pith.science/pith/DUOH24XMGTITU5NFM33QW7AK3J/action/author_attestation","sign_citation":"https://pith.science/pith/DUOH24XMGTITU5NFM33QW7AK3J/action/citation_signature","submit_replication":"https://pith.science/pith/DUOH24XMGTITU5NFM33QW7AK3J/action/replication_record"}},"created_at":"2026-07-05T05:19:09.396136+00:00","updated_at":"2026-07-05T05:19:09.396136+00:00"}