论文标题
生成对抗网络的游戏理论方法
A game-theoretic approach for Generative Adversarial Networks
论文作者
论文摘要
生成对抗网络（GAN）是一类生成模型，以生成准确的样品而闻名。甘斯的关键特征是有两个拮抗神经网络：发生器和歧视者。实施的主要瓶颈是神经网络很难训练。提高性能的一种方法是为对抗过程设计可靠的算法。由于训练可以作为随机的纳什均衡问题施放，因此我们将其重写为变异不等式，并引入算法来计算近似解决方案。具体而言，我们提出了一种用于gans的随机放松前向后算法。我们证明，当游戏的假映射是单调的时，我们会收敛到精确的解决方案或在其附近。
Generative adversarial networks (GANs) are a class of generative models, known for producing accurate samples. The key feature of GANs is that there are two antagonistic neural networks: the generator and the discriminator. The main bottleneck for their implementation is that the neural networks are very hard to train. One way to improve their performance is to design reliable algorithms for the adversarial process. Since the training can be cast as a stochastic Nash equilibrium problem, we rewrite it as a variational inequality and introduce an algorithm to compute an approximate solution. Specifically, we propose a stochastic relaxed forward-backward algorithm for GANs. We prove that when the pseudogradient mapping of the game is monotone, we have convergence to an exact solution or in a neighbourhood of it.
