{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7WUMOM7IWOC7ZTHFMGMSKN2DZD","short_pith_number":"pith:7WUMOM7I","schema_version":"1.0","canonical_sha256":"fda8c733e8b385fccce56199253743c8c5879bd6c0a052d7f978cbaba37e2631","source":{"kind":"arxiv","id":"1806.07104","version":1},"attestation_state":"computed","paper":{"title":"Online Linear Quadratic Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alon Cohen, Avinatan Hassidim, Kunal Talwar, Nevena Lazic, Tomer Koren, Yishay Mansour","submitted_at":"2018-06-19T08:42:45Z","abstract_excerpt":"We study the problem of controlling linear time-invariant systems with known noisy dynamics and adversarially chosen quadratic losses. We present the first efficient online learning algorithms in this setting that guarantee $O(\\sqrt{T})$ regret under mild assumptions, where $T$ is the time horizon. Our algorithms rely on a novel SDP relaxation for the steady-state distribution of the system. Crucially, and in contrast to previously proposed relaxations, the feasible solutions of our SDP all correspond to \"strongly stable\" policies that mix exponentially fast to a steady state."},"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":"1806.07104","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T08:42:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"129838c1e4d2f43c5ece582377ba2c30b8ff2d09e0d0bdc211764471d3791dec","abstract_canon_sha256":"7d9c5d20fb935d80b4d00b1ef06ce0d66a527ced03f965377d51bd82f8ce623a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:51.860239Z","signature_b64":"5nX1FJXeCur64136j+CSLw//sE1EDNQAuKIzMSzWXihqafC6bZnYz71DBdMuYWV0QQltIlH24hymUozRo/5cCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fda8c733e8b385fccce56199253743c8c5879bd6c0a052d7f978cbaba37e2631","last_reissued_at":"2026-05-18T00:12:51.859761Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:51.859761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Linear Quadratic Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alon Cohen, Avinatan Hassidim, Kunal Talwar, Nevena Lazic, Tomer Koren, Yishay Mansour","submitted_at":"2018-06-19T08:42:45Z","abstract_excerpt":"We study the problem of controlling linear time-invariant systems with known noisy dynamics and adversarially chosen quadratic losses. We present the first efficient online learning algorithms in this setting that guarantee $O(\\sqrt{T})$ regret under mild assumptions, where $T$ is the time horizon. Our algorithms rely on a novel SDP relaxation for the steady-state distribution of the system. Crucially, and in contrast to previously proposed relaxations, the feasible solutions of our SDP all correspond to \"strongly stable\" policies that mix exponentially fast to a steady state."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.07104","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":"1806.07104","created_at":"2026-05-18T00:12:51.859842+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.07104v1","created_at":"2026-05-18T00:12:51.859842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07104","created_at":"2026-05-18T00:12:51.859842+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WUMOM7IWOC7","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WUMOM7IWOC7ZTHF","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WUMOM7I","created_at":"2026-05-18T12:32:11.075285+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/7WUMOM7IWOC7ZTHFMGMSKN2DZD","json":"https://pith.science/pith/7WUMOM7IWOC7ZTHFMGMSKN2DZD.json","graph_json":"https://pith.science/api/pith-number/7WUMOM7IWOC7ZTHFMGMSKN2DZD/graph.json","events_json":"https://pith.science/api/pith-number/7WUMOM7IWOC7ZTHFMGMSKN2DZD/events.json","paper":"https://pith.science/paper/7WUMOM7I"},"agent_actions":{"view_html":"https://pith.science/pith/7WUMOM7IWOC7ZTHFMGMSKN2DZD","download_json":"https://pith.science/pith/7WUMOM7IWOC7ZTHFMGMSKN2DZD.json","view_paper":"https://pith.science/paper/7WUMOM7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.07104&json=true","fetch_graph":"https://pith.science/api/pith-number/7WUMOM7IWOC7ZTHFMGMSKN2DZD/graph.json","fetch_events":"https://pith.science/api/pith-number/7WUMOM7IWOC7ZTHFMGMSKN2DZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WUMOM7IWOC7ZTHFMGMSKN2DZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WUMOM7IWOC7ZTHFMGMSKN2DZD/action/storage_attestation","attest_author":"https://pith.science/pith/7WUMOM7IWOC7ZTHFMGMSKN2DZD/action/author_attestation","sign_citation":"https://pith.science/pith/7WUMOM7IWOC7ZTHFMGMSKN2DZD/action/citation_signature","submit_replication":"https://pith.science/pith/7WUMOM7IWOC7ZTHFMGMSKN2DZD/action/replication_record"}},"created_at":"2026-05-18T00:12:51.859842+00:00","updated_at":"2026-05-18T00:12:51.859842+00:00"}