{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6JSCSMYM5CZ2ERYKXRLHUAGWKC","short_pith_number":"pith:6JSCSMYM","schema_version":"1.0","canonical_sha256":"f26429330ce8b3a2470abc567a00d6508f2511331b1d0bf07cf5384beaf62e39","source":{"kind":"arxiv","id":"1901.08779","version":2},"attestation_state":"computed","paper":{"title":"Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen-Yu Wei, Haipeng Luo, Julian Zimmert","submitted_at":"2019-01-25T08:30:59Z","abstract_excerpt":"We develop the first general semi-bandit algorithm that simultaneously achieves $\\mathcal{O}(\\log T)$ regret for stochastic environments and $\\mathcal{O}(\\sqrt{T})$ regret for adversarial environments without knowledge of the regime or the number of rounds $T$. The leading problem-dependent constants of our bounds are not only optimal in some worst-case sense studied previously, but also optimal for two concrete instances of semi-bandit problems. Our algorithm and analysis extend the recent work of (Zimmert & Seldin, 2019) for the special case of multi-armed bandit, but importantly requires a "},"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":"1901.08779","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T08:30:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ac7cfb8828b7c088dfa395656922230eabd6bd4730e5dca507066d1b5ccad924","abstract_canon_sha256":"323e8e7e4a07f588963b0f24c63ab867b4938acc3a05ef784115cd532db8338e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:21.588591Z","signature_b64":"h0ke5hf2DWojjCA7za0Sno67grFxb+McUg5CSjx3STDwGgqMtia29spjHOOJPnKdfrzI7HneRXlTcr0qyKHhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f26429330ce8b3a2470abc567a00d6508f2511331b1d0bf07cf5384beaf62e39","last_reissued_at":"2026-07-05T00:07:21.588143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:21.588143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen-Yu Wei, Haipeng Luo, Julian Zimmert","submitted_at":"2019-01-25T08:30:59Z","abstract_excerpt":"We develop the first general semi-bandit algorithm that simultaneously achieves $\\mathcal{O}(\\log T)$ regret for stochastic environments and $\\mathcal{O}(\\sqrt{T})$ regret for adversarial environments without knowledge of the regime or the number of rounds $T$. The leading problem-dependent constants of our bounds are not only optimal in some worst-case sense studied previously, but also optimal for two concrete instances of semi-bandit problems. Our algorithm and analysis extend the recent work of (Zimmert & Seldin, 2019) for the special case of multi-armed bandit, but importantly requires a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08779","kind":"arxiv","version":2},"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/1901.08779/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":"1901.08779","created_at":"2026-07-05T00:07:21.588197+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08779v2","created_at":"2026-07-05T00:07:21.588197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08779","created_at":"2026-07-05T00:07:21.588197+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JSCSMYM5CZ2","created_at":"2026-07-05T00:07:21.588197+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JSCSMYM5CZ2ERYK","created_at":"2026-07-05T00:07:21.588197+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JSCSMYM","created_at":"2026-07-05T00:07:21.588197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14953","citing_title":"Efficient Online Conformal Selection with Limited Feedback","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6JSCSMYM5CZ2ERYKXRLHUAGWKC","json":"https://pith.science/pith/6JSCSMYM5CZ2ERYKXRLHUAGWKC.json","graph_json":"https://pith.science/api/pith-number/6JSCSMYM5CZ2ERYKXRLHUAGWKC/graph.json","events_json":"https://pith.science/api/pith-number/6JSCSMYM5CZ2ERYKXRLHUAGWKC/events.json","paper":"https://pith.science/paper/6JSCSMYM"},"agent_actions":{"view_html":"https://pith.science/pith/6JSCSMYM5CZ2ERYKXRLHUAGWKC","download_json":"https://pith.science/pith/6JSCSMYM5CZ2ERYKXRLHUAGWKC.json","view_paper":"https://pith.science/paper/6JSCSMYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08779&json=true","fetch_graph":"https://pith.science/api/pith-number/6JSCSMYM5CZ2ERYKXRLHUAGWKC/graph.json","fetch_events":"https://pith.science/api/pith-number/6JSCSMYM5CZ2ERYKXRLHUAGWKC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JSCSMYM5CZ2ERYKXRLHUAGWKC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JSCSMYM5CZ2ERYKXRLHUAGWKC/action/storage_attestation","attest_author":"https://pith.science/pith/6JSCSMYM5CZ2ERYKXRLHUAGWKC/action/author_attestation","sign_citation":"https://pith.science/pith/6JSCSMYM5CZ2ERYKXRLHUAGWKC/action/citation_signature","submit_replication":"https://pith.science/pith/6JSCSMYM5CZ2ERYKXRLHUAGWKC/action/replication_record"}},"created_at":"2026-07-05T00:07:21.588197+00:00","updated_at":"2026-07-05T00:07:21.588197+00:00"}