Research map / Bandits and online learning / Online convex optimization and games
Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits
Julian Zimmert, Yevgeny Seldin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use RV loss estimators instead of IW estimators in Tsallis-INF | Tsallis-INF (alpha=1/2) · Stochastic bandits (simulation) | pseudo-regret | Improved |
| Tsallis-INF with RV estimators compared to UCB1, Exp3, Exp3++, Broad | Tsallis-INF · Stochastic bandits (simulation) | pseudo-regret | Improved |
| Tsallis-INF vs Thompson Sampling in stochastically constrained adversarial environment | Thompson Sampling · Stochastically constrained adversarial bandits (simulation) | pseudo-regret | Hurt |
| increase number of copies of the best arm (non-unique optimal arm) (ablation) | Tsallis-INF · Multiple optimal arms (simulation) | pseudo-regret | Improved |
Closest papers by meaning
- Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously (ICML 2019 · similarity 0.91)
- Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting (NeurIPS 2024 · similarity 0.90)
- Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback (NeurIPS 2025 · similarity 0.90)
- Stochastic Bandits Robust to Adversarial Attacks (ICLR 2025 · similarity 0.90)
- Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints (NeurIPS 2024 · similarity 0.89)
- Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays (NeurIPS 2026 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
