Class-conditioned Domain Generalization via Wasserstein Distributional Robust Optimization
Given multiple source domains, domain generalization aims at learning a universal model that performs well on any unseen but related target domain. In this work, we focus on the domain generalization scenario where domain shifts occur among class-conditional distributions of different domains. Existing approaches are not sufficiently robust when the variation of conditional distributions given the same class is large. In this work, we extend the concept of distributional robust optimization to solve the class-conditional domain generalization problem. Our approach optimizes the worst-case performance of a classifier over class-conditional distributions within a Wasserstein ball centered around the barycenter of the source conditional distributions. We also propose an iterative algorithm for learning the optimal radius of the Wasserstein balls automatically. Experiments show that the proposed framework has better performance on unseen target domain than approaches without domain generalization.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain GeneralizationSimilar Papers 제목 키워드 기반
Generalizing to Unseen Domains with Wasserstein Distributional Robustness under Limited Source Knowledge
Domain generalization aims at learning a universal model that performs well on unseen target domains, incorporating knowledge from multiple source domains. In this research, we consider the scenario where different domai…
Domain GeneralizationRotated MNISTTest-time AdaptationExact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models
Wasserstein distributionally robust estimators have emerged as powerful models for prediction and decision-making under uncertainty. These estimators provide attractive generalization guarantees: the robust objective obt…
Decision MakingDecision Making Under UncertaintyOn Generalization and Regularization via Wasserstein Distributionally Robust Optimization
Wasserstein distributionally robust optimization (DRO) has gained prominence in operations research and machine learning as a powerful method for achieving solutions with favorable out-of-sample performance. Two compelli…
Generalization BoundsMinimax Statistical Learning with Wasserstein Distances
As opposed to standard empirical risk minimization (ERM), distributionally robust optimization aims to minimize the worst-case risk over a larger ambiguity set containing the original empirical distribution of the traini…
Domain AdaptationGeneralization BoundsOn Distributional Reinforcement Learning in Chaotic Dynamical Systems
Chaotic dynamical systems pose a fundamental challenge for Reinforcement Learning (RL): exponential sensitivity to initial conditions induces high-variance bootstrap targets and poorly conditioned gradient updates. Chaot…
Reinforcement Learning