Research map / Bandits and online learning / Multi-armed bandits
On Minimizing Regret in Fixed-Confidence $\varepsilon$-Best Arm Identification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies fixed-confidence epsilon-best arm identification with the objective of minimizing cumulative regret incurred while identifying an epsilon-best arm, rather than sample complexity alone.
Problem
Fixed-confidence epsilon-best arm identification in K-armed bandits is usually framed as minimizing sample complexity; this paper instead targets the cumulative regret incurred during the identification process.
Approach
Shifts the objective from sample complexity to cumulative regret of identifying an epsilon-best arm in the asymptotic regime where the error probability delta goes to zero.
Experimental setup
Metrics: cumulative regret sample complexity
Closest papers by meaning
- Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification? (NeurIPS 2026 · similarity 0.92)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.92)
- Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits (NeurIPS 2024 · similarity 0.91)
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.91)
- Fixed-Budget Differentially Private Best Arm Identification (ICLR 2024 · similarity 0.91)
- Fixed Confidence Best Arm Identification in the Bayesian Setting (NeurIPS 2024 · similarity 0.91)
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.