{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XM7M26ZON4BG7V33WTOEL6IYAH","short_pith_number":"pith:XM7M26ZO","schema_version":"1.0","canonical_sha256":"bb3ecd7b2e6f026fd77bb4dc45f91801e554660a1efaf1922913cb72e6fe677f","source":{"kind":"arxiv","id":"2004.13465","version":1},"attestation_state":"computed","paper":{"title":"Nearly Optimal Regret for Stochastic Linear Bandits with Heavy-Tailed Payoffs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Xue, Guanghui Wang, Lijun Zhang, Yimu Wang","submitted_at":"2020-04-28T13:01:38Z","abstract_excerpt":"In this paper, we study the problem of stochastic linear bandits with finite action sets. Most of existing work assume the payoffs are bounded or sub-Gaussian, which may be violated in some scenarios such as financial markets. To settle this issue, we analyze the linear bandits with heavy-tailed payoffs, where the payoffs admit finite $1+\\epsilon$ moments for some $\\epsilon\\in(0,1]$. Through median of means and dynamic truncation, we propose two novel algorithms which enjoy a sublinear regret bound of $\\widetilde{O}(d^{\\frac{1}{2}}T^{\\frac{1}{1+\\epsilon}})$, where $d$ is the dimension of conte"},"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":"2004.13465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-28T13:01:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b945d4a83dc84801ec339f6e18bcf2b07cfd23e27b9212e63696603992cf9f7e","abstract_canon_sha256":"d93764fc450a52716035e380b58fd26a2ee764e408de6998bdada6060ac6ccf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:59.635475Z","signature_b64":"xxdJzdL6mQsx/dRIibjCpLt8Ax6gAD/H+PUxOU3f0YyB0KHY4f0clEL2b5Ube1qaWgij7Eu9hpi3D160I1xrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb3ecd7b2e6f026fd77bb4dc45f91801e554660a1efaf1922913cb72e6fe677f","last_reissued_at":"2026-07-05T00:58:59.635080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:59.635080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nearly Optimal Regret for Stochastic Linear Bandits with Heavy-Tailed Payoffs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Xue, Guanghui Wang, Lijun Zhang, Yimu Wang","submitted_at":"2020-04-28T13:01:38Z","abstract_excerpt":"In this paper, we study the problem of stochastic linear bandits with finite action sets. Most of existing work assume the payoffs are bounded or sub-Gaussian, which may be violated in some scenarios such as financial markets. To settle this issue, we analyze the linear bandits with heavy-tailed payoffs, where the payoffs admit finite $1+\\epsilon$ moments for some $\\epsilon\\in(0,1]$. Through median of means and dynamic truncation, we propose two novel algorithms which enjoy a sublinear regret bound of $\\widetilde{O}(d^{\\frac{1}{2}}T^{\\frac{1}{1+\\epsilon}})$, where $d$ is the dimension of conte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13465","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.13465/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2004.13465","created_at":"2026-07-05T00:58:59.635137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.13465v1","created_at":"2026-07-05T00:58:59.635137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13465","created_at":"2026-07-05T00:58:59.635137+00:00"},{"alias_kind":"pith_short_12","alias_value":"XM7M26ZON4BG","created_at":"2026-07-05T00:58:59.635137+00:00"},{"alias_kind":"pith_short_16","alias_value":"XM7M26ZON4BG7V33","created_at":"2026-07-05T00:58:59.635137+00:00"},{"alias_kind":"pith_short_8","alias_value":"XM7M26ZO","created_at":"2026-07-05T00:58:59.635137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02486","citing_title":"Catoni Contextual Bandits are Robust to Heavy-tailed Rewards","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XM7M26ZON4BG7V33WTOEL6IYAH","json":"https://pith.science/pith/XM7M26ZON4BG7V33WTOEL6IYAH.json","graph_json":"https://pith.science/api/pith-number/XM7M26ZON4BG7V33WTOEL6IYAH/graph.json","events_json":"https://pith.science/api/pith-number/XM7M26ZON4BG7V33WTOEL6IYAH/events.json","paper":"https://pith.science/paper/XM7M26ZO"},"agent_actions":{"view_html":"https://pith.science/pith/XM7M26ZON4BG7V33WTOEL6IYAH","download_json":"https://pith.science/pith/XM7M26ZON4BG7V33WTOEL6IYAH.json","view_paper":"https://pith.science/paper/XM7M26ZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.13465&json=true","fetch_graph":"https://pith.science/api/pith-number/XM7M26ZON4BG7V33WTOEL6IYAH/graph.json","fetch_events":"https://pith.science/api/pith-number/XM7M26ZON4BG7V33WTOEL6IYAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XM7M26ZON4BG7V33WTOEL6IYAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XM7M26ZON4BG7V33WTOEL6IYAH/action/storage_attestation","attest_author":"https://pith.science/pith/XM7M26ZON4BG7V33WTOEL6IYAH/action/author_attestation","sign_citation":"https://pith.science/pith/XM7M26ZON4BG7V33WTOEL6IYAH/action/citation_signature","submit_replication":"https://pith.science/pith/XM7M26ZON4BG7V33WTOEL6IYAH/action/replication_record"}},"created_at":"2026-07-05T00:58:59.635137+00:00","updated_at":"2026-07-05T00:58:59.635137+00:00"}