Counterfactual explanations are attracting significant attention due to the flourishing
applications of machine learning models in consequential domains. A counterfactual plan …

We study optimization problems whereby the optimization variable is a probability measure.
Since the probability space is not a vector space, many classical and powerful methods for …

Distributionally robust control (DRC) aims to effectively manage distributional ambiguity in
stochastic systems. While most existing works address inaccurate distributional information …

Principal component analysis is a simple yet useful dimensionality reduction technique in
modern machine learning pipelines. In consequential domains such as college admission …

We study linear regression problems infβ∈ Rd(EPn [| Y− X β| r]) 1/r+ δρ (β), with r≥ 1,
convex penalty ρ, and empirical measure of the data Pn. Well known examples include the …

This article focuses on a class of distributionally robust optimization (DRO) problems where,
unlike the growing body of the literature, the objective function is potentially nonlinear in the …

Safety is one of the main challenges when applying learning-based motion controllers to
practical robotic systems, especially when the dynamics of the robots and their surrounding …

A recourse action aims to explain a particular algorithmic decision by showing one specific
way in which the instance could be modified to receive an alternate outcome. Existing …

Precise control under uncertainty requires a good understanding and characterization of the
noise affecting the system. This paper studies the problem of steering state distributions of …

This letter reports new properties of the Wasserstein/Gelbrich distance and associated
ambiguity sets to analyze the correlation between two scalar random variables. A simple …