Taehyun Cho

PhD student, Seoul National University

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Pareto Optimal Risk-Agnostic Distributional Bandits with Heavy-Tail Rewards

#3104 · Kyungjae Lee, Dohyeong Kim, Taehyun Cho, Chaeyeon Kim, Yunkyung Ko, Seungyub Han, Seokhun Ju, Dohyeok Lee, Sungbin Lim

We propose DistLCB, a multi-risk bandit algorithm for heavy-tailed rewards that leverages Wasserstein-based confidence bounds to achieve Pareto-optimality and provable regret guarantees.