{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BHZGYWUTVGSYS6KB2AXLBIVGNJ","short_pith_number":"pith:BHZGYWUT","schema_version":"1.0","canonical_sha256":"09f26c5a93a9a5897941d02eb0a2a66a69c5d194337040c6c4a51c05aa6fb2b1","source":{"kind":"arxiv","id":"2011.05944","version":4},"attestation_state":"computed","paper":{"title":"Asymptotically Optimal Information-Directed Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Claire Vernade, Csaba Szepesv\\'ari, Johannes Kirschner, Tor Lattimore","submitted_at":"2020-11-11T18:01:59Z","abstract_excerpt":"We introduce a simple and efficient algorithm for stochastic linear bandits with finitely many actions that is asymptotically optimal and (nearly) worst-case optimal in finite time. The approach is based on the frequentist information-directed sampling (IDS) framework, with a surrogate for the information gain that is informed by the optimization problem that defines the asymptotic lower bound. Our analysis sheds light on how IDS balances the trade-off between regret and information and uncovers a surprising connection between the recently proposed primal-dual methods and the IDS algorithm. We"},"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":"2011.05944","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-11-11T18:01:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"58c61ce3802051e89eeecd8aea4e0f658d5bde3fa758ab48209542dab7647d82","abstract_canon_sha256":"7926078d574746533a0f737ccd7ef4f81e38aacdf4172a7e209bfe3a25bdc5da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:29.550465Z","signature_b64":"7Vzpq2xrJVPxjA2rWiJcJMHqyOsP0J86ujQ3hVQxqYBobaV43LfgnTsJktjnyjaH8zTJSWsXHY7IHueymwxKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09f26c5a93a9a5897941d02eb0a2a66a69c5d194337040c6c4a51c05aa6fb2b1","last_reissued_at":"2026-07-05T02:54:29.549986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:29.549986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymptotically Optimal Information-Directed Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Claire Vernade, Csaba Szepesv\\'ari, Johannes Kirschner, Tor Lattimore","submitted_at":"2020-11-11T18:01:59Z","abstract_excerpt":"We introduce a simple and efficient algorithm for stochastic linear bandits with finitely many actions that is asymptotically optimal and (nearly) worst-case optimal in finite time. The approach is based on the frequentist information-directed sampling (IDS) framework, with a surrogate for the information gain that is informed by the optimization problem that defines the asymptotic lower bound. Our analysis sheds light on how IDS balances the trade-off between regret and information and uncovers a surprising connection between the recently proposed primal-dual methods and the IDS algorithm. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05944","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/2011.05944/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":"2011.05944","created_at":"2026-07-05T02:54:29.550043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.05944v4","created_at":"2026-07-05T02:54:29.550043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05944","created_at":"2026-07-05T02:54:29.550043+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHZGYWUTVGSY","created_at":"2026-07-05T02:54:29.550043+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHZGYWUTVGSYS6KB","created_at":"2026-07-05T02:54:29.550043+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHZGYWUT","created_at":"2026-07-05T02:54:29.550043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21841","citing_title":"An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BHZGYWUTVGSYS6KB2AXLBIVGNJ","json":"https://pith.science/pith/BHZGYWUTVGSYS6KB2AXLBIVGNJ.json","graph_json":"https://pith.science/api/pith-number/BHZGYWUTVGSYS6KB2AXLBIVGNJ/graph.json","events_json":"https://pith.science/api/pith-number/BHZGYWUTVGSYS6KB2AXLBIVGNJ/events.json","paper":"https://pith.science/paper/BHZGYWUT"},"agent_actions":{"view_html":"https://pith.science/pith/BHZGYWUTVGSYS6KB2AXLBIVGNJ","download_json":"https://pith.science/pith/BHZGYWUTVGSYS6KB2AXLBIVGNJ.json","view_paper":"https://pith.science/paper/BHZGYWUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.05944&json=true","fetch_graph":"https://pith.science/api/pith-number/BHZGYWUTVGSYS6KB2AXLBIVGNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BHZGYWUTVGSYS6KB2AXLBIVGNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHZGYWUTVGSYS6KB2AXLBIVGNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHZGYWUTVGSYS6KB2AXLBIVGNJ/action/storage_attestation","attest_author":"https://pith.science/pith/BHZGYWUTVGSYS6KB2AXLBIVGNJ/action/author_attestation","sign_citation":"https://pith.science/pith/BHZGYWUTVGSYS6KB2AXLBIVGNJ/action/citation_signature","submit_replication":"https://pith.science/pith/BHZGYWUTVGSYS6KB2AXLBIVGNJ/action/replication_record"}},"created_at":"2026-07-05T02:54:29.550043+00:00","updated_at":"2026-07-05T02:54:29.550043+00:00"}