A Provably Convergent and Practical Algorithm for Min-max Optimization with Applications to GANs

by   Oren Mangoubi, et al.

We present a new algorithm for optimizing min-max loss functions that arise in training GANs. We prove that our algorithm converges to an equilibrium point in time polynomial in the dimension, and smoothness parameters of the loss function. The point our algorithm converges to is stable when the maximizing player can respond using any sequence of steps which increase the loss at each step, and the minimizing player is empowered to simulate the maximizing player's response for arbitrarily many steps but is restricted to move according to updates sampled from a stochastic gradient oracle. We apply our algorithm to train GANs on Gaussian mixtures, MNIST and CIFAR-10. We observe that our algorithm trains stably and avoids mode collapse, while achieving a training time per iteration and memory requirement similar to gradient descent-ascent.


page 11

page 12

page 30

page 31

page 32

page 33

page 34


Direct-Search for a Class of Stochastic Min-Max Problems

Recent applications in machine learning have renewed the interest of the...

Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function

Computing Nash equilibrium (NE) of multi-player games has witnessed rene...

A Second-order Equilibrium in Nonconvex-Nonconcave Min-max Optimization: Existence and Algorithm

Min-max optimization, with a nonconvex-nonconcave objective function f: ...

Solving a class of non-convex min-max games using iterative first order methods

Recent applications that arise in machine learning have surged significa...

Minimax Optimization with Smooth Algorithmic Adversaries

This paper considers minimax optimization min_x max_y f(x, y) in the cha...

α-GAN: Convergence and Estimation Guarantees

We prove a two-way correspondence between the min-max optimization of ge...