# EVaR-Optimal Arm Identification in Bandits

arXiv: https://arxiv.org/abs/2510.04728 · HTML: https://mlsanity.com/paper/2510.04728/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 17 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Builds on (most cited first, 4 of 4)

- [Optimal Best Arm Identification with Fixed Confidence](https://mlsanity.com/paper/1602.04589/) (2016)
- [Optimal Thompson Sampling strategies for support-aware CVaR bandits](https://mlsanity.com/paper/2012.05754/) (2020)
- [Optimal Best-Arm Identification Methods for Tail-Risk Measures](https://mlsanity.com/paper/2008.07606/) (2020)
- [Beyond Average Return in Markov Decision Processes](https://mlsanity.com/paper/2310.20266/) (2023)

## Abstract (arXiv)

We study the fixed-confidence best arm identification (BAI) problem within the multi-armed bandit (MAB) framework under the Entropic Value-at-Risk (EVaR) criterion. Our analysis considers a nonparametric setting, allowing for general reward distributions bounded in [0,1]. This formulation addresses the critical need for risk-averse decision-making in high-stakes environments, such as finance, moving beyond simple expected value optimization. We propose a δ-correct, Track-and-Stop based algorithm and derive a corresponding lower bound on the expected sample complexity, which we prove is asymptotically matched. The implementation of our algorithm and the characterization of the lower bound both require solving a complex convex optimization problem and a related, simpler non-convex one.