paper-with-me

Papers

Wasserstein Distributionally Robust Optimization: A Three-Player Game Framework

2021-01-01 · Zhuozhuo Tu, Shan You, Tao Huang, DaCheng Tao

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bridging Bayesian and Minimax Mean Square Error Estimation via Wasserstein Distributionally Robust Optimization

2019-11-08 · Viet Anh Nguyen, Soroosh Shafieezadeh-Abadeh, Daniel Kuhn, Peyman Mohajerin Esfahani

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

2026-02-23 · Guixian Chen, Salar Fattahi, Soroosh Shafiee arxiv

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

2019-06-04 · Jose Blanchet, Karthyek Murthy, Nian Si

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

2022-04-30 · Luhao Zhang, Jincheng Yang, Rui Gao

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

2025-01-06 · Yu Chen, Yuda Li, ShaoYuan Li, Xiang Yin

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…