{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KAYOKKOHUJROQTZHHM5IX7UVRF","short_pith_number":"pith:KAYOKKOH","schema_version":"1.0","canonical_sha256":"5030e529c7a262e84f273b3a8bfe95896ea97f54bb7a0db2b958b742c70aad4f","source":{"kind":"arxiv","id":"2203.04274","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Initial Hints for Free in Stochastic Linear Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Abhimanyu Das, Ashok Cutkosky, Chris Dann, Qiuyi (Richard) Zhang","submitted_at":"2022-03-08T18:48:55Z","abstract_excerpt":"We study the setting of optimizing with bandit feedback with additional prior knowledge provided to the learner in the form of an initial hint of the optimal action. We present a novel algorithm for stochastic linear bandits that uses this hint to improve its regret to $\\tilde O(\\sqrt{T})$ when the hint is accurate, while maintaining a minimax-optimal $\\tilde O(d\\sqrt{T})$ regret independent of the quality of the hint. Furthermore, we provide a Pareto frontier of tight tradeoffs between best-case and worst-case regret, with matching lower bounds. Perhaps surprisingly, our work shows that lever"},"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":"2203.04274","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-08T18:48:55Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"376482a2a4527ec0a81d35492ca3e2ac10e32b46bf4859a22338effbae845aff","abstract_canon_sha256":"3ab28544a165457f0570be0f18cebfb9e4ffb5f80fd1f1a2e1e828dc26cd390f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:07.734876Z","signature_b64":"V68XqCOR6uBh7bWZjE1ZcDXPPZY4CeOBJSEW+hSBbme3Jgf06aO1NFf5Yh02NKDBB7isetwTUIghlzw7FcS3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5030e529c7a262e84f273b3a8bfe95896ea97f54bb7a0db2b958b742c70aad4f","last_reissued_at":"2026-07-05T04:03:07.734489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:07.734489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Initial Hints for Free in Stochastic Linear Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Abhimanyu Das, Ashok Cutkosky, Chris Dann, Qiuyi (Richard) Zhang","submitted_at":"2022-03-08T18:48:55Z","abstract_excerpt":"We study the setting of optimizing with bandit feedback with additional prior knowledge provided to the learner in the form of an initial hint of the optimal action. We present a novel algorithm for stochastic linear bandits that uses this hint to improve its regret to $\\tilde O(\\sqrt{T})$ when the hint is accurate, while maintaining a minimax-optimal $\\tilde O(d\\sqrt{T})$ regret independent of the quality of the hint. Furthermore, we provide a Pareto frontier of tight tradeoffs between best-case and worst-case regret, with matching lower bounds. Perhaps surprisingly, our work shows that lever"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.04274","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/2203.04274/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":"2203.04274","created_at":"2026-07-05T04:03:07.734547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.04274v1","created_at":"2026-07-05T04:03:07.734547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.04274","created_at":"2026-07-05T04:03:07.734547+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAYOKKOHUJRO","created_at":"2026-07-05T04:03:07.734547+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAYOKKOHUJROQTZH","created_at":"2026-07-05T04:03:07.734547+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAYOKKOH","created_at":"2026-07-05T04:03:07.734547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAYOKKOHUJROQTZHHM5IX7UVRF","json":"https://pith.science/pith/KAYOKKOHUJROQTZHHM5IX7UVRF.json","graph_json":"https://pith.science/api/pith-number/KAYOKKOHUJROQTZHHM5IX7UVRF/graph.json","events_json":"https://pith.science/api/pith-number/KAYOKKOHUJROQTZHHM5IX7UVRF/events.json","paper":"https://pith.science/paper/KAYOKKOH"},"agent_actions":{"view_html":"https://pith.science/pith/KAYOKKOHUJROQTZHHM5IX7UVRF","download_json":"https://pith.science/pith/KAYOKKOHUJROQTZHHM5IX7UVRF.json","view_paper":"https://pith.science/paper/KAYOKKOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.04274&json=true","fetch_graph":"https://pith.science/api/pith-number/KAYOKKOHUJROQTZHHM5IX7UVRF/graph.json","fetch_events":"https://pith.science/api/pith-number/KAYOKKOHUJROQTZHHM5IX7UVRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAYOKKOHUJROQTZHHM5IX7UVRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAYOKKOHUJROQTZHHM5IX7UVRF/action/storage_attestation","attest_author":"https://pith.science/pith/KAYOKKOHUJROQTZHHM5IX7UVRF/action/author_attestation","sign_citation":"https://pith.science/pith/KAYOKKOHUJROQTZHHM5IX7UVRF/action/citation_signature","submit_replication":"https://pith.science/pith/KAYOKKOHUJROQTZHHM5IX7UVRF/action/replication_record"}},"created_at":"2026-07-05T04:03:07.734547+00:00","updated_at":"2026-07-05T04:03:07.734547+00:00"}