HessianFR: An Efficient Hessian-based Follow-the-Ridge Algorithm for Minimax Optimization
This addresses the challenge of finding local equilibria in sequential games for applications like image generation, though it appears incremental as it builds on existing Hessian-based methods.
The paper tackles the problem of efficiently solving minimax optimization in sequential games, such as those in GAN training, by proposing HessianFR, a Hessian-based algorithm that outperforms baselines in convergence and image generation quality on datasets like MNIST, CIFAR-10, and CelebA.
Wide applications of differentiable two-player sequential games (e.g., image generation by GANs) have raised much interest and attention of researchers to study efficient and fast algorithms. Most of the existing algorithms are developed based on nice properties of simultaneous games, i.e., convex-concave payoff functions, but are not applicable in solving sequential games with different settings. Some conventional gradient descent ascent algorithms theoretically and numerically fail to find the local Nash equilibrium of the simultaneous game or the local minimax (i.e., local Stackelberg equilibrium) of the sequential game. In this paper, we propose the HessianFR, an efficient Hessian-based Follow-the-Ridge algorithm with theoretical guarantees. Furthermore, the convergence of the stochastic algorithm and the approximation of Hessian inverse are exploited to improve algorithm efficiency. A series of experiments of training generative adversarial networks (GANs) have been conducted on both synthetic and real-world large-scale image datasets (e.g. MNIST, CIFAR-10 and CelebA). The experimental results demonstrate that the proposed HessianFR outperforms baselines in terms of convergence and image generation quality.