Log In Sign Up

A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems

by   Jiawei Zhang, et al.

Nonconvex-concave min-max problem arises in many machine learning applications including minimizing a pointwise maximum of a set of nonconvex functions and robust adversarial training of neural networks. A popular approach to solve this problem is the gradient descent-ascent (GDA) algorithm which unfortunately can exhibit oscillation in case of nonconvexity. In this paper, we introduce a "smoothing" scheme which can be combined with GDA to stabilize the oscillation and ensure convergence to a stationary solution. We prove that the stabilized GDA algorithm can achieve an O(1/ϵ^2) iteration complexity for minimizing the pointwise maximum of a finite collection of nonconvex functions. Moreover, the smoothed GDA algorithm achieves an O(1/ϵ^4) iteration complexity for general nonconvex-concave problems. Extensions of this stabilized GDA algorithm to multi-block cases are presented. To the best of our knowledge, this is the first algorithm to achieve O(1/ϵ^2) for a class of nonconvex-concave problem. We illustrate the practical efficiency of the stabilized GDA algorithm on robust training.


page 1

page 2

page 3

page 4


On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems

We consider nonconvex-concave minimax problems, _x_y∈Y f(x, y), where f ...

Min-Max Bilevel Multi-objective Optimization with Applications in Machine Learning

This paper is the first to propose a generic min-max bilevel multi-objec...

Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization

The use of min-max optimization in adversarial training of deep neural n...

On Robustness in Nonconvex Optimization with Application to Defense Planning

In the context of structured nonconvex optimization, we estimate the inc...

Enhanced First and Zeroth Order Variance Reduced Algorithms for Min-Max Optimization

Min-max optimization captures many important machine learning problems s...

Recursive Decomposition for Nonconvex Optimization

Continuous optimization is an important problem in many areas of AI, inc...

A SMART Stochastic Algorithm for Nonconvex Optimization with Applications to Robust Machine Learning

In this paper, we show how to transform any optimization problem that ar...