We propose and analyze algorithms for distributionally robust optimization of convex losses
with conditional value at risk (CVaR) and $\chi^ 2$ divergence uncertainty sets. We prove …

Spurious correlations pose a major challenge for robust machine learning. Models trained
with empirical risk minimization (ERM) may learn to rely on correlations between class …

Abstract Domain generalization (DG) seeks predictors which perform well on unseen test
distributions by leveraging data drawn from multiple related training distributions or …

In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the
returns. A risk measure often focuses on the worst returns out of the agent's experience. As a …

Many of the successes of machine learning are based on minimizing an averaged loss
function. However, it is well-known that this paradigm suffers from robustness issues that …

Training Reinforcement Learning (RL) agents in high-stakes applications might be too
prohibitive due to the risk associated to exploration. Thus, the agent can only use data …

Recent works have revealed an essential paradigm in designing loss functions that
differentiate individual losses versus aggregate losses. The individual loss measures the …

Exponential tilting is a technique commonly used in fields such as statistics, probability,
information theory, and optimization to create parametric distribution shifts. Despite its …

Even when unable to run experiments, practitioners can evaluate prospective policies, using
previously logged data. However, while the bandits literature has adopted a diverse set of …

We present a federated learning framework that allows one to handle heterogeneous client
devices that may not conform to the population data distribution. The proposed approach …