{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:LCCPKQD4CJO67J3NS33G46VBLD","short_pith_number":"pith:LCCPKQD4","schema_version":"1.0","canonical_sha256":"5884f5407c125defa76d96f66e7aa158cf692cb189047117aac34d3a7416aed8","source":{"kind":"arxiv","id":"1102.2670","version":1},"attestation_state":"computed","paper":{"title":"Online Least Squares Estimation with Self-Normalized Processes: An Application to Bandit Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Csaba Szepesvari, David Pal, Yasin Abbasi-Yadkori","submitted_at":"2011-02-14T04:06:31Z","abstract_excerpt":"The analysis of online least squares estimation is at the heart of many stochastic sequential decision making problems. We employ tools from the self-normalized processes to provide a simple and self-contained proof of a tail bound of a vector-valued martingale. We use the bound to construct a new tighter confidence sets for the least squares estimate.\n  We apply the confidence sets to several online decision problems, such as the multi-armed and the linearly parametrized bandit problems. The confidence sets are potentially applicable to other problems such as sleeping bandits, generalized lin"},"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":"1102.2670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-02-14T04:06:31Z","cross_cats_sorted":[],"title_canon_sha256":"3f6212e2672855b834331f0b3ee70deb8d3424a573e928820141190503b9f86d","abstract_canon_sha256":"c442a10511709aa063e409100749485161f950832ac659ad1fab7d47b8f7c066"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:28:46.752508Z","signature_b64":"Bsztlx8ch6SHnz/KPXb+Lrkv35UqWHqwXja81S1BcR6e5Pv58L8WsGMEgHA5g5XdpeBjL7ad6GZaUNB/wIQ8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5884f5407c125defa76d96f66e7aa158cf692cb189047117aac34d3a7416aed8","last_reissued_at":"2026-05-18T04:28:46.752045Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:28:46.752045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Least Squares Estimation with Self-Normalized Processes: An Application to Bandit Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Csaba Szepesvari, David Pal, Yasin Abbasi-Yadkori","submitted_at":"2011-02-14T04:06:31Z","abstract_excerpt":"The analysis of online least squares estimation is at the heart of many stochastic sequential decision making problems. We employ tools from the self-normalized processes to provide a simple and self-contained proof of a tail bound of a vector-valued martingale. We use the bound to construct a new tighter confidence sets for the least squares estimate.\n  We apply the confidence sets to several online decision problems, such as the multi-armed and the linearly parametrized bandit problems. The confidence sets are potentially applicable to other problems such as sleeping bandits, generalized lin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1102.2670","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":""},"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":"1102.2670","created_at":"2026-05-18T04:28:46.752098+00:00"},{"alias_kind":"arxiv_version","alias_value":"1102.2670v1","created_at":"2026-05-18T04:28:46.752098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1102.2670","created_at":"2026-05-18T04:28:46.752098+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCCPKQD4CJO6","created_at":"2026-05-18T12:26:34.985390+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCCPKQD4CJO67J3N","created_at":"2026-05-18T12:26:34.985390+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCCPKQD4","created_at":"2026-05-18T12:26:34.985390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.04565","citing_title":"Adapt and Stabilize, Then Learn and Optimize: A New Approach to Adaptive LQR","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04477","citing_title":"Data-dependent Exploration for Online Reinforcement Learning from Human Feedback","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21270","citing_title":"CLT-Optimal Parameter Error Bounds for Linear System Identification","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCCPKQD4CJO67J3NS33G46VBLD","json":"https://pith.science/pith/LCCPKQD4CJO67J3NS33G46VBLD.json","graph_json":"https://pith.science/api/pith-number/LCCPKQD4CJO67J3NS33G46VBLD/graph.json","events_json":"https://pith.science/api/pith-number/LCCPKQD4CJO67J3NS33G46VBLD/events.json","paper":"https://pith.science/paper/LCCPKQD4"},"agent_actions":{"view_html":"https://pith.science/pith/LCCPKQD4CJO67J3NS33G46VBLD","download_json":"https://pith.science/pith/LCCPKQD4CJO67J3NS33G46VBLD.json","view_paper":"https://pith.science/paper/LCCPKQD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1102.2670&json=true","fetch_graph":"https://pith.science/api/pith-number/LCCPKQD4CJO67J3NS33G46VBLD/graph.json","fetch_events":"https://pith.science/api/pith-number/LCCPKQD4CJO67J3NS33G46VBLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCCPKQD4CJO67J3NS33G46VBLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCCPKQD4CJO67J3NS33G46VBLD/action/storage_attestation","attest_author":"https://pith.science/pith/LCCPKQD4CJO67J3NS33G46VBLD/action/author_attestation","sign_citation":"https://pith.science/pith/LCCPKQD4CJO67J3NS33G46VBLD/action/citation_signature","submit_replication":"https://pith.science/pith/LCCPKQD4CJO67J3NS33G46VBLD/action/replication_record"}},"created_at":"2026-05-18T04:28:46.752098+00:00","updated_at":"2026-05-18T04:28:46.752098+00:00"}