A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial Networks
Abstract
A novel first-order method is proposed for training generative adversarial networks (GANs). It modifies the Gauss-Newton method to approximate the min-max Hessian and uses the Sherman-Morrison inversion formula to calculate the inverse. The method corresponds to a fixed-point method that ensures necessary contraction. To evaluate its effectiveness, numerical experiments are conducted on various datasets commonly used in image generation tasks, such as MNIST, Fashion MNIST, CIFAR10, FFHQ, and LSUN. Our method is capable of generating high-fidelity images with greater diversity across multiple datasets. It also achieves the highest inception score for CIFAR10 among all compared methods, including state-of-the-art second-order methods. Additionally, its execution time is comparable to that of first-order min-max methods.
Keywords
Cite
@article{arxiv.2404.07172,
title = {A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial Networks},
author = {Neel Mishra and Bamdev Mishra and Pratik Jawanpuria and Pawan Kumar},
journal= {arXiv preprint arXiv:2404.07172},
year = {2024}
}
Comments
accepted in IJCNN 2023, 9 pages