{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:5ICT36MXQ5MBXQXG22QAGLIMY2","short_pith_number":"pith:5ICT36MX","schema_version":"1.0","canonical_sha256":"ea053df99787581bc2e6d6a0032d0cc6a624d843df075ccbaa9686a66bd8a51f","source":{"kind":"arxiv","id":"1604.05257","version":3},"attestation_state":"computed","paper":{"title":"Risk-Averse Multi-Armed Bandit Problems under Mean-Variance Measure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qing Zhao, Sattar Vakili","submitted_at":"2016-04-18T17:28:41Z","abstract_excerpt":"The multi-armed bandit problems have been studied mainly under the measure of expected total reward accrued over a horizon of length $T$. In this paper, we address the issue of risk in multi-armed bandit problems and develop parallel results under the measure of mean-variance, a commonly adopted risk measure in economics and mathematical finance. We show that the model-specific regret and the model-independent regret in terms of the mean-variance of the reward process are lower bounded by $\\Omega(\\log T)$ and $\\Omega(T^{2/3})$, respectively. We then show that variations of the UCB policy and t"},"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":"1604.05257","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-18T17:28:41Z","cross_cats_sorted":[],"title_canon_sha256":"8971ea8489b4460e6226be6a1ee3f02479f867261789d4decb5021082268e061","abstract_canon_sha256":"30af60d665872aafe836b523f1c09ddf18ae09a7a16c710c763bd36314b6c3df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:04.466978Z","signature_b64":"Vb6u5JB8PigfCsJKnuyKS5YqKPtnzZncddBHZi2eMUUkctvMIU5wIOTkkJvGCEkRrbdbi/Ig2E5p/9F+iT8vCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea053df99787581bc2e6d6a0032d0cc6a624d843df075ccbaa9686a66bd8a51f","last_reissued_at":"2026-05-18T00:38:04.466289Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:04.466289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk-Averse Multi-Armed Bandit Problems under Mean-Variance Measure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qing Zhao, Sattar Vakili","submitted_at":"2016-04-18T17:28:41Z","abstract_excerpt":"The multi-armed bandit problems have been studied mainly under the measure of expected total reward accrued over a horizon of length $T$. In this paper, we address the issue of risk in multi-armed bandit problems and develop parallel results under the measure of mean-variance, a commonly adopted risk measure in economics and mathematical finance. We show that the model-specific regret and the model-independent regret in terms of the mean-variance of the reward process are lower bounded by $\\Omega(\\log T)$ and $\\Omega(T^{2/3})$, respectively. We then show that variations of the UCB policy and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.05257","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":"1604.05257","created_at":"2026-05-18T00:38:04.466392+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.05257v3","created_at":"2026-05-18T00:38:04.466392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.05257","created_at":"2026-05-18T00:38:04.466392+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ICT36MXQ5MB","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ICT36MXQ5MBXQXG","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ICT36MX","created_at":"2026-05-18T12:30:01.593930+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/5ICT36MXQ5MBXQXG22QAGLIMY2","json":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2.json","graph_json":"https://pith.science/api/pith-number/5ICT36MXQ5MBXQXG22QAGLIMY2/graph.json","events_json":"https://pith.science/api/pith-number/5ICT36MXQ5MBXQXG22QAGLIMY2/events.json","paper":"https://pith.science/paper/5ICT36MX"},"agent_actions":{"view_html":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2","download_json":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2.json","view_paper":"https://pith.science/paper/5ICT36MX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.05257&json=true","fetch_graph":"https://pith.science/api/pith-number/5ICT36MXQ5MBXQXG22QAGLIMY2/graph.json","fetch_events":"https://pith.science/api/pith-number/5ICT36MXQ5MBXQXG22QAGLIMY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2/action/storage_attestation","attest_author":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2/action/author_attestation","sign_citation":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2/action/citation_signature","submit_replication":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2/action/replication_record"}},"created_at":"2026-05-18T00:38:04.466392+00:00","updated_at":"2026-05-18T00:38:04.466392+00:00"}