Standard federated optimization methods successfully apply to stochastic problems with
single-level structure. However, many contemporary ML problems-including adversarial …

The minimax problems arise throughout machine learning applications, ranging from
adversarial training and policy evaluation in reinforcement learning to AUROC …

In this paper, we consider nonconvex minimax optimization, which is gaining prominence in
many modern machine learning applications, such as GANs. Large-scale edge-based …

We consider distributed stochastic variational inequalities (VIs) on unbounded domains with
the problem data that is heterogeneous (non-IID) and distributed across many devices. We …

Minimax optimization has seen a surge in interest with the advent of modern applications
such as GANs, and it is inherently more challenging than simple minimization. The difficulty …

We present Scaff-PD, a fast and communication-efficient algorithm for distributionally robust
federated learning. Our approach improves fairness by optimizing a family of distributionally …

Variational inequalities in general and saddle point problems in particular are increasingly
relevant in machine learning applications, including adversarial learning, GANs, transport …

This paper focuses on the distributed optimization of stochastic saddle point problems. The
first part of the paper is devoted to lower bounds for the cenralized and decentralized …

Variational inequalities are a broad and flexible class of problems that includes
minimization, saddle point, and fixed point problems as special cases. Therefore, variational …

Fair prediction across protected groups is an important consideration in federated learning
applications. In this work we propose a general framework for provably fair federated …