Limiting Behaviors of Nonconvex-Nonconcave Minimax Optimization via Continuous-Time Systems

by   Benjamin Grimmer, et al.

Unlike nonconvex optimization, where gradient descent is guaranteed to converge to a local optimizer, algorithms for nonconvex-nonconcave minimax optimization can have topologically different solution paths: sometimes converging to a solution, sometimes never converging and instead following a limit cycle, and sometimes diverging. In this paper, we study the limiting behaviors of three classic minimax algorithms: gradient decent ascent (GDA), alternating gradient decent ascent (AGDA), and the extragradient method (EGM). Numerically, we observe that all of these limiting behaviors can arise in Generative Adversarial Networks (GAN) training. To explain these different behaviors, we study the high-order resolution continuous-time dynamics that correspond to each algorithm, which results in the sufficient (and almost necessary) conditions for the local convergence by each method. Moreover, this ODE perspective allows us to characterize the phase transition between these different limiting behaviors caused by introducing regularization in the problem instance.



page 1

page 2

page 3

page 4


Solve Minimax Optimization by Anderson Acceleration

Many modern machine learning algorithms such as generative adversarial n...

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

Nonconvex minimax problems appear frequently in emerging machine learnin...

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

Alternating gradient-descent-ascent (AltGDA) is an optimization algorith...

The Landscape of Nonconvex-Nonconcave Minimax Optimization

Minimax optimization has become a central tool for modern machine learni...

Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry

The gradient descent-ascent (GDA) algorithm has been widely applied to s...

K-Beam Subgradient Descent for Minimax Optimization

Minimax optimization plays a key role in adversarial training of machine...

Semi-Implicit Hybrid Gradient Methods with Application to Adversarial Robustness

Adversarial examples, crafted by adding imperceptible perturbations to n...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.