Graph neural networks (GNNs) which apply the deep neural networks to graph data have
achieved significant performance for the task of semi-supervised node classification …

Recent applications that arise in machine learning have surged significant interest in solving
min-max saddle point games. This problem has been extensively studied in the convex …

Min–max problems have broad applications in machine learning, including learning with
non-decomposable loss and learning with robustness to data distribution. Convex–concave …

The min-max problem, also known as the saddle point problem, is a class of optimization
problems which minimizes and maximizes two subsets of variables simultaneously. This …

We propose an efficient algorithm for finding first-order Nash equilibria in min-max problems
of the form \textstylex∈Xy∈YF(x,y), where the objective function is smooth in both variables …

In this paper, we study the problem of constrained min-max optimization in a black-box
setting, where the desired optimizer cannot access the gradients of the objective function but …

Adaptive gradient algorithms perform gradient-based updates using the history of gradients
and are ubiquitous in training deep neural networks. While adaptive gradient methods …

Abstract Generative Adversarial Networks (GANs) are a powerful class of generative models
in the deep learning community. Current practice on large-scale GAN training utilizes large …

This paper presents smoothing schemes for obtaining approximate stationary points of
unconstrained or linearly constrained composite nonconvex-concave min-max (and hence …

Min-max optimization problems (ie, min-max games) have been attracting a great deal of
attention because of their applicability to a wide range of machine learning problems …