Wasserstein Distributionally Robust Optimization: A Three-Player Game Framework
Wasserstein distributionally robust optimization (DRO) has recently received significant attention in machine learning due to its connection to generalization, robustness and regularization. Existing methods only consider a limited class of loss functions or apply to small values of robustness. In this paper, we present a three-player game framework for solving Wasserstein DRO problem with arbitrary level of robustness, which can handle general loss functions. Specifically, we formulate a min-max game between three players who optimize over probability measures, model parameters and Lagrange multipliers. We also propose new algorithms for finding an equilibrium of the game in convex and non-convex settings which both enjoy provable convergence guarantees. Furthermore, we prove an excess risk bound for the proposed algorithms which shows that the solution returned by the algorithms closely achieves the optimal minimax risk.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Bridging Bayesian and Minimax Mean Square Error Estimation via Wasserstein Distributionally Robust Optimization
We introduce a distributionally robust minimium mean square error estimation model with a Wasserstein ambiguity set to recover an unknown signal from a noisy observation. The proposed model can be viewed as a zero-sum ga…
Wasserstein Distributionally Robust Online Learning
We study distributionally robust online learning, where a risk-averse learner updates decisions sequentially to guard against worst-case distributions drawn from a Wasserstein ambiguity set centered at past observations.…
Confidence Regions in Wasserstein Distributionally Robust Estimation
Wasserstein distributionally robust optimization estimators are obtained as solutions of min-max problems in which the statistician selects a parameter minimizing the worst-case loss among all probability models within a…
A Short and General Duality Proof for Wasserstein Distributionally Robust Optimization
We present a general duality result for Wasserstein distributionally robust optimization that holds for any Kantorovich transport cost, measurable loss function, and nominal probability distribution. Assuming an intercha…
Distributionally Robust Control Synthesis for Stochastic Systems with Safety and Reach-Avoid Specifications
We investigate the problem of synthesizing distributionally robust control policies for stochastic systems under safety and reach-avoid specifications. Using a game-theoretical framework, we consider the setting where th…