A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial Networks
This work addresses the challenge of stable and efficient GAN training for image generation, representing an incremental improvement over existing methods.
The paper tackles the problem of training generative adversarial networks (GANs) by proposing a novel first-order method based on a modified Gauss-Newton approach, which achieves the highest inception score on CIFAR10 and generates high-fidelity, diverse images across multiple datasets with execution time comparable to first-order methods.
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.