Research map / Bandits and online learning / Online convex optimization and games
Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously
Julian Zimmert, Haipeng Luo, Chen-Yu Wei
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 Hybrid instead of Exp2 or LogBarrier | m-set with d=10, m=5, T=10^7 · Stochastic environment | average pseudo-regret | Improved |
| Use Hybrid instead of CombUCB | m-set with d=10, m=5, T=10^7 · Stochastic environment | average pseudo-regret | No clear effect |
| Use Thompson Sampling in place of Hybrid | m-set with d=10, m=5, T=10^7 · Stochastic environment | average pseudo-regret | Improved |
| Use CombUCB or Thompson Sampling instead of Hybrid | m-set with d=10, m=5, T=10^7 · Stochastically constrained adversarial setting | average pseudo-regret | Hurt |
Closest papers by meaning
- Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback (NeurIPS 2025 · similarity 0.92)
- Adversarial Combinatorial Semi-bandits with Graph Feedback (ICML 2025 · similarity 0.91)
- Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints (NeurIPS 2024 · similarity 0.91)
- Follow-the-Perturbed-Leader Nearly Achieves Best-of-Both-Worlds for the m-Set Semi-Bandit Problems (NeurIPS 2025 · similarity 0.91)
- Stochastic Bandits Robust to Adversarial Attacks (ICLR 2025 · similarity 0.91)
- Tight Rates for Bandit Control Beyond Quadratics (NeurIPS 2024 · similarity 0.90)
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.
