{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:Q5G7W55JFDMY3ZPTPFI5TJN7PV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fe475e932834c11fe62096255cfb8a54271b6f2ce3598c054b27d6290885e464","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-14T16:12:09Z","title_canon_sha256":"7510092912f3e8da99b9b6c4658875be15436cfbe12efe05d29871ce0964e79a"},"schema_version":"1.0","source":{"id":"1202.3079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.3079","created_at":"2026-05-18T04:02:24Z"},{"alias_kind":"arxiv_version","alias_value":"1202.3079v1","created_at":"2026-05-18T04:02:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.3079","created_at":"2026-05-18T04:02:24Z"},{"alias_kind":"pith_short_12","alias_value":"Q5G7W55JFDMY","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"Q5G7W55JFDMY3ZPT","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"Q5G7W55J","created_at":"2026-05-18T12:27:18Z"}],"graph_snapshots":[{"event_id":"sha256:c92633e6c83375cf6b29bae8f332457cf94d49ebe43a1d3f574437a9826a81c5","target":"graph","created_at":"2026-05-18T04:02:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We address the online linear optimization problem with bandit feedback. Our contribution is twofold. First, we provide an algorithm (based on exponential weights) with a regret of order $\\sqrt{d n \\log N}$ for any finite action set with $N$ actions, under the assumption that the instantaneous loss is bounded by 1. This shaves off an extraneous $\\sqrt{d}$ factor compared to previous works, and gives a regret bound of order $d \\sqrt{n \\log n}$ for any compact set of actions. Without further assumptions on the action set, this last bound is minimax optimal up to a logarithmic factor. Interestingl","authors_text":"Nicol\\`o Cesa-Bianchi, S\\'ebastien Bubeck, Sham M. Kakade","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-14T16:12:09Z","title":"Towards minimax policies for online linear optimization with bandit feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.3079","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:56c5cb1c741e7d7fd21ec8a7e28c518bdb0786d622cdaf4bccd0be6e70a6c713","target":"record","created_at":"2026-05-18T04:02:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fe475e932834c11fe62096255cfb8a54271b6f2ce3598c054b27d6290885e464","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-14T16:12:09Z","title_canon_sha256":"7510092912f3e8da99b9b6c4658875be15436cfbe12efe05d29871ce0964e79a"},"schema_version":"1.0","source":{"id":"1202.3079","kind":"arxiv","version":1}},"canonical_sha256":"874dfb77a928d98de5f37951d9a5bf7d6626a43f89afa1594ac783cf33b6abd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"874dfb77a928d98de5f37951d9a5bf7d6626a43f89afa1594ac783cf33b6abd4","first_computed_at":"2026-05-18T04:02:24.158562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:02:24.158562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kPERdob3qJmnbbcl3aRebJAcNevSZXlR22oKasn2jUHrA9OyKyWff8iclILl3hLWPmYm8sTRUMUCeliqHBRcAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T04:02:24.159368Z","signed_message":"canonical_sha256_bytes"},"source_id":"1202.3079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56c5cb1c741e7d7fd21ec8a7e28c518bdb0786d622cdaf4bccd0be6e70a6c713","sha256:c92633e6c83375cf6b29bae8f332457cf94d49ebe43a1d3f574437a9826a81c5"],"state_sha256":"c8f8390c8de49e1f5c49f75fa7a9aa1cfed9ccc633abca9ebae45270f10f4072"}