{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:J6FMIMROWYFUGOKLUPETOGT5JC","short_pith_number":"pith:J6FMIMRO","schema_version":"1.0","canonical_sha256":"4f8ac4322eb60b43394ba3c9371a7d4887e17b34e60d43115a7b9a870313a92e","source":{"kind":"arxiv","id":"1608.03023","version":3},"attestation_state":"computed","paper":{"title":"Stochastic Rank-1 Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Claire Vernade, Csaba Szepesvari, Sumeet Katariya, Zheng Wen","submitted_at":"2016-08-10T01:51:36Z","abstract_excerpt":"We propose stochastic rank-$1$ bandits, a class of online learning problems where at each step a learning agent chooses a pair of row and column arms, and receives the product of their values as a reward. The main challenge of the problem is that the individual values of the row and column are unobserved. We assume that these values are stochastic and drawn independently. We propose a computationally-efficient algorithm for solving our problem, which we call Rank1Elim. We derive a $O((K + L) (1 / \\Delta) \\log n)$ upper bound on its $n$-step regret, where $K$ is the number of rows, $L$ is the n"},"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":"1608.03023","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-10T01:51:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8ca9e89e78dc95691b2ecdf0e20933b495f8feb60322414e7c7b210220a3cce1","abstract_canon_sha256":"e6c63a928131737500229ec6b1d9d4fff82cdee6863abe9a91ac8847ae1a8cd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:06.643567Z","signature_b64":"YL7evKb7A1iuj/VobsVF1AF9gPJlphLvVuv8JhiPIJIVlh9EUhwVE1vHuJIvaPBk3ImvlxwYF4g0gflKKRreAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f8ac4322eb60b43394ba3c9371a7d4887e17b34e60d43115a7b9a870313a92e","last_reissued_at":"2026-05-18T00:49:06.643040Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:06.643040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Rank-1 Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Claire Vernade, Csaba Szepesvari, Sumeet Katariya, Zheng Wen","submitted_at":"2016-08-10T01:51:36Z","abstract_excerpt":"We propose stochastic rank-$1$ bandits, a class of online learning problems where at each step a learning agent chooses a pair of row and column arms, and receives the product of their values as a reward. The main challenge of the problem is that the individual values of the row and column are unobserved. We assume that these values are stochastic and drawn independently. We propose a computationally-efficient algorithm for solving our problem, which we call Rank1Elim. We derive a $O((K + L) (1 / \\Delta) \\log n)$ upper bound on its $n$-step regret, where $K$ is the number of rows, $L$ is the n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.03023","kind":"arxiv","version":3},"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":"1608.03023","created_at":"2026-05-18T00:49:06.643109+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.03023v3","created_at":"2026-05-18T00:49:06.643109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.03023","created_at":"2026-05-18T00:49:06.643109+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6FMIMROWYFU","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6FMIMROWYFUGOKL","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6FMIMRO","created_at":"2026-05-18T12:30:22.444734+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/J6FMIMROWYFUGOKLUPETOGT5JC","json":"https://pith.science/pith/J6FMIMROWYFUGOKLUPETOGT5JC.json","graph_json":"https://pith.science/api/pith-number/J6FMIMROWYFUGOKLUPETOGT5JC/graph.json","events_json":"https://pith.science/api/pith-number/J6FMIMROWYFUGOKLUPETOGT5JC/events.json","paper":"https://pith.science/paper/J6FMIMRO"},"agent_actions":{"view_html":"https://pith.science/pith/J6FMIMROWYFUGOKLUPETOGT5JC","download_json":"https://pith.science/pith/J6FMIMROWYFUGOKLUPETOGT5JC.json","view_paper":"https://pith.science/paper/J6FMIMRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.03023&json=true","fetch_graph":"https://pith.science/api/pith-number/J6FMIMROWYFUGOKLUPETOGT5JC/graph.json","fetch_events":"https://pith.science/api/pith-number/J6FMIMROWYFUGOKLUPETOGT5JC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6FMIMROWYFUGOKLUPETOGT5JC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6FMIMROWYFUGOKLUPETOGT5JC/action/storage_attestation","attest_author":"https://pith.science/pith/J6FMIMROWYFUGOKLUPETOGT5JC/action/author_attestation","sign_citation":"https://pith.science/pith/J6FMIMROWYFUGOKLUPETOGT5JC/action/citation_signature","submit_replication":"https://pith.science/pith/J6FMIMROWYFUGOKLUPETOGT5JC/action/replication_record"}},"created_at":"2026-05-18T00:49:06.643109+00:00","updated_at":"2026-05-18T00:49:06.643109+00:00"}