{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OXTFDPXHUGQSCQJKF2JCHO5JU5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b693d38188ce43d1d2bfb80fcb85e03f90bc6c27a72dd39be480f032e0c98832","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-19T19:42:19Z","title_canon_sha256":"bbe00de8f526c85e81447af529a277bf3642a79c140cfe74dc00314f41fcdac2"},"schema_version":"1.0","source":{"id":"1807.07623","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.07623","created_at":"2026-07-05T04:01:28Z"},{"alias_kind":"arxiv_version","alias_value":"1807.07623v6","created_at":"2026-07-05T04:01:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.07623","created_at":"2026-07-05T04:01:28Z"},{"alias_kind":"pith_short_12","alias_value":"OXTFDPXHUGQS","created_at":"2026-07-05T04:01:28Z"},{"alias_kind":"pith_short_16","alias_value":"OXTFDPXHUGQSCQJK","created_at":"2026-07-05T04:01:28Z"},{"alias_kind":"pith_short_8","alias_value":"OXTFDPXH","created_at":"2026-07-05T04:01:28Z"}],"graph_snapshots":[{"event_id":"sha256:82b42200157748bcc8426748303ad41eface35c04fd970c3613925e009639945","target":"graph","created_at":"2026-07-05T04:01:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1807.07623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We derive an algorithm that achieves the optimal (within constants) pseudo-regret in both adversarial and stochastic multi-armed bandits without prior knowledge of the regime and time horizon. The algorithm is based on online mirror descent (OMD) with Tsallis entropy regularization with power $\\alpha=1/2$ and reduced-variance loss estimators. More generally, we define an adversarial regime with a self-bounding constraint, which includes stochastic regime, stochastically constrained adversarial regime (Wei and Luo), and stochastic regime with adversarial corruptions (Lykouris et al.) as special","authors_text":"Julian Zimmert, Yevgeny Seldin","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-19T19:42:19Z","title":"Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.07623","kind":"arxiv","version":6},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cecdfd73b7ce6bc2cb941470104baca7eb00d4dcbfdbcafae923cd336fbbd6a1","target":"record","created_at":"2026-07-05T04:01:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b693d38188ce43d1d2bfb80fcb85e03f90bc6c27a72dd39be480f032e0c98832","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-19T19:42:19Z","title_canon_sha256":"bbe00de8f526c85e81447af529a277bf3642a79c140cfe74dc00314f41fcdac2"},"schema_version":"1.0","source":{"id":"1807.07623","kind":"arxiv","version":6}},"canonical_sha256":"75e651bee7a1a121412a2e9223bba9a7745b07a8882bef43368b530570d8c7fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75e651bee7a1a121412a2e9223bba9a7745b07a8882bef43368b530570d8c7fc","first_computed_at":"2026-07-05T04:01:28.745472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:28.745472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vU41dCTHUdjnCxNqI88spN7GrzLssIfb6kehVKV0Q99l6zg83BbKw7mDdo443Zj6T8ufZWXhL+VJ2GbfYcxODA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:28.745958Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.07623","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cecdfd73b7ce6bc2cb941470104baca7eb00d4dcbfdbcafae923cd336fbbd6a1","sha256:82b42200157748bcc8426748303ad41eface35c04fd970c3613925e009639945"],"state_sha256":"5bf9ab3dc1b24ab2fbbfbdf3c8eef2a01583845716c68435461f489d9be83354"}