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 …
S Lu, I Tsaknakis, M Hong… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
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 …
D Goktas, A Greenwald - Advances in Neural Information …, 2021 - proceedings.neurips.cc
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 …