Accelerated Proximal Alternating Gradient-Descent-Ascent for Nonconvex Minimax Machine Learning

12/22/2021
∙
by   Ziyi Chen, et al.
∙
0
∙

Alternating gradient-descent-ascent (AltGDA) is an optimization algorithm that has been widely used for model training in various machine learning applications, which aim to solve a nonconvex minimax optimization problem. However, the existing studies show that it suffers from a high computation complexity in nonconvex minimax optimization. In this paper, we develop a single-loop and fast AltGDA-type algorithm that leverages proximal gradient updates and momentum acceleration to solve regularized nonconvex minimax optimization problems. By identifying the intrinsic Lyapunov function of this algorithm, we prove that it converges to a critical point of the nonconvex minimax optimization problem and achieves a computation complexity 𝒪(κ^1.5ϵ^-2), where ϵ is the desired level of accuracy and κ is the problem's condition number. Such a computation complexity improves the state-of-the-art complexities of single-loop GDA and AltGDA algorithms (see the summary of comparison in Table 1). We demonstrate the effectiveness of our algorithm via an experiment on adversarial deep learning.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
∙ 03/07/2023

Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization

In the paper, we study a class of nonconvex nonconcave minimax optimizat...
research
∙ 10/04/2016

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...
research
∙ 02/09/2021

Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry

The gradient descent-ascent (GDA) algorithm has been widely applied to s...
research
∙ 02/22/2020

Global Convergence and Variance-Reduced Optimization for a Class of Nonconvex-Nonconcave Minimax Problems

Nonconvex minimax problems appear frequently in emerging machine learnin...
research
∙ 05/29/2018

K-Beam Subgradient Descent for Minimax Optimization

Minimax optimization plays a key role in adversarial training of machine...
research
∙ 12/10/2021

Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity

Gradient descent ascent (GDA), the simplest single-loop algorithm for no...
research
∙ 05/26/2023

Submodular Minimax Optimization: Finding Effective Sets

Despite the rich existing literature about minimax optimization in conti...

Please sign up or login with your details

Forgot password? Click here to reset