Research map / Bandits and online learning / Multi-armed bandits
Non-Asymptotic Analysis of a UCB-based Top Two Algorithm
Marc Jourdan, Rémy Degenne
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 TTUCB (UCB leader) instead of other Top Two algorithms (TTTS, T3C, beta-EB-TCI) | Top Two best arm identification · Random Gaussian instances, K=10, delta=0.1 | empirical stopping time | No clear effect |
| Use TTUCB instead of Track-and-Stop and FWS | Top Two best arm identification · Random Gaussian instances, K=10, delta=0.1 | empirical stopping time | Improved |
| Use TTUCB instead of DKM, LUCB, 1/2-LUCB and uniform sampling | Top Two best arm identification · Random Gaussian instances, K=10, delta=0.1 | empirical stopping time | Improved |
| Use UCB leader (TTUCB) instead of Thompson sampling leader (T3C) as number of arms grows | Top Two best arm identification · 1-sparse instances, increasing K | empirical stopping time | Hurt |
| Increase number of arms K on 1-sparse instances | all compared algorithms · 1-sparse instances | empirical stopping time | No clear effect |
Closest papers by meaning
- Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits (NeurIPS 2026 · similarity 0.91)
- On Universally Optimal Algorithms for A/B Testing (ICML 2024 · similarity 0.89)
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.89)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.88)
- Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification? (NeurIPS 2026 · similarity 0.88)
- Optimal Top-Two Method for Best Arm Identification and Fluid Analysis (NeurIPS 2024 · similarity 0.88)
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.
