{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:DIHX7US6LCN7Y3VFVNUMWXITHJ","short_pith_number":"pith:DIHX7US6","schema_version":"1.0","canonical_sha256":"1a0f7fd25e589bfc6ea5ab68cb5d133a4b71115e3cfaf16b0c51db613a6ea859","source":{"kind":"arxiv","id":"1605.08722","version":1},"attestation_state":"computed","paper":{"title":"An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao-Kai Chiang, Peter Auer","submitted_at":"2016-05-27T17:28:35Z","abstract_excerpt":"We present an algorithm that achieves almost optimal pseudo-regret bounds against adversarial and stochastic bandits. Against adversarial bandits the pseudo-regret is $O(K\\sqrt{n \\log n})$ and against stochastic bandits the pseudo-regret is $O(\\sum_i (\\log n)/\\Delta_i)$. We also show that no algorithm with $O(\\log n)$ pseudo-regret against stochastic bandits can achieve $\\tilde{O}(\\sqrt{n})$ expected regret against adaptive adversarial bandits. This complements previous results of Bubeck and Slivkins (2012) that show $\\tilde{O}(\\sqrt{n})$ expected adversarial regret with $O((\\log n)^2)$ stocha"},"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":"1605.08722","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-27T17:28:35Z","cross_cats_sorted":[],"title_canon_sha256":"cf474215827177e79c896a85bbb83b503ac61feeddf25a09e862403cc55153fc","abstract_canon_sha256":"b2f5044317a741fc831badc93d0d6366335878a3953e4c2a501ac1b29f9a4b80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:29.223185Z","signature_b64":"I5iEXYTRt2dHYVatSidwY2LpHk5Su32qYcHT1HLhKrgJ0g+gHyYgN6DAZ7YbLTkhW6cmQdHIWbgBuDvN4AtAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a0f7fd25e589bfc6ea5ab68cb5d133a4b71115e3cfaf16b0c51db613a6ea859","last_reissued_at":"2026-05-18T01:13:29.222614Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:29.222614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao-Kai Chiang, Peter Auer","submitted_at":"2016-05-27T17:28:35Z","abstract_excerpt":"We present an algorithm that achieves almost optimal pseudo-regret bounds against adversarial and stochastic bandits. Against adversarial bandits the pseudo-regret is $O(K\\sqrt{n \\log n})$ and against stochastic bandits the pseudo-regret is $O(\\sum_i (\\log n)/\\Delta_i)$. We also show that no algorithm with $O(\\log n)$ pseudo-regret against stochastic bandits can achieve $\\tilde{O}(\\sqrt{n})$ expected regret against adaptive adversarial bandits. This complements previous results of Bubeck and Slivkins (2012) that show $\\tilde{O}(\\sqrt{n})$ expected adversarial regret with $O((\\log n)^2)$ stocha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.08722","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":""},"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":"1605.08722","created_at":"2026-05-18T01:13:29.222712+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.08722v1","created_at":"2026-05-18T01:13:29.222712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08722","created_at":"2026-05-18T01:13:29.222712+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIHX7US6LCN7","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIHX7US6LCN7Y3VF","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIHX7US6","created_at":"2026-05-18T12:30:12.583610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25272","citing_title":"Spectral bandits","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19672","citing_title":"Budgeted Online Influence Maximization","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14860","citing_title":"Best of both worlds: Stochastic & adversarial best-arm identification","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DIHX7US6LCN7Y3VFVNUMWXITHJ","json":"https://pith.science/pith/DIHX7US6LCN7Y3VFVNUMWXITHJ.json","graph_json":"https://pith.science/api/pith-number/DIHX7US6LCN7Y3VFVNUMWXITHJ/graph.json","events_json":"https://pith.science/api/pith-number/DIHX7US6LCN7Y3VFVNUMWXITHJ/events.json","paper":"https://pith.science/paper/DIHX7US6"},"agent_actions":{"view_html":"https://pith.science/pith/DIHX7US6LCN7Y3VFVNUMWXITHJ","download_json":"https://pith.science/pith/DIHX7US6LCN7Y3VFVNUMWXITHJ.json","view_paper":"https://pith.science/paper/DIHX7US6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.08722&json=true","fetch_graph":"https://pith.science/api/pith-number/DIHX7US6LCN7Y3VFVNUMWXITHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DIHX7US6LCN7Y3VFVNUMWXITHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIHX7US6LCN7Y3VFVNUMWXITHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIHX7US6LCN7Y3VFVNUMWXITHJ/action/storage_attestation","attest_author":"https://pith.science/pith/DIHX7US6LCN7Y3VFVNUMWXITHJ/action/author_attestation","sign_citation":"https://pith.science/pith/DIHX7US6LCN7Y3VFVNUMWXITHJ/action/citation_signature","submit_replication":"https://pith.science/pith/DIHX7US6LCN7Y3VFVNUMWXITHJ/action/replication_record"}},"created_at":"2026-05-18T01:13:29.222712+00:00","updated_at":"2026-05-18T01:13:29.222712+00:00"}