← Search

Yunkyung Ko

2 accepted papers

2025

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

NeurIPS 2025poster

This paper addresses the problem of multi-risk measure agnostic multi-armed bandits in heavy-tailed reward settings. We propose a framework that leverages novel deviation inequalities for the $1$-Wasserstein distance to construct confidence intervals for Lipschitz risk measures. The distributional…

Cited by 0SourceScholar
2025

Score-informed Neural Operator for Enhancing Ordering-based Causal Discovery

NeurIPS 2025poster

Ordering-based approaches to causal discovery identify topological orders of causal graphs, providing scalable alternatives to combinatorial search methods. Under the Additive Noise Models (ANMs) assumption, recent causal ordering methods based on score matching require an accurate estimation of the…

Cited by 0SourceScholar