论文标题
走向甘斯的近似能力
Towards GANs' Approximation Ability
论文作者
论文摘要
生成对抗网络（GAN）对生成模型领域引起了强烈的兴趣。然而，据报道，很少有针对理论分析或算法设计的研究据报道了gan发电机的近似能力。本文将首先分析GAN的近似属性。类似于具有一个隐藏层的完全连接的神经网络的通用近似属性，我们证明，gan中具有输入潜在变量的发电机可以普遍近似鉴于增加的隐藏神经元的潜在数据分布。此外，我们提出了一种名为随机数据生成（SDG）的方法，以增强gans'Approximation能力。我们的方法是基于通过在gan中通过数据生成来实现随机性的简单想法，该想法通过对层之间的条件概率进行了先验分布。可以通过使用重新运动技巧轻松实现可持续发展目标方法。合成数据集的实验结果验证了通过这种可持续发展目标方法获得的提高近似能力。在实用数据集中，当模型体系结构较小时，使用可持续发展目标的四个gan也可以优于相应的传统gan。
Generative adversarial networks (GANs) have attracted intense interest in the field of generative models. However, few investigations focusing either on the theoretical analysis or on algorithm design for the approximation ability of the generator of GANs have been reported. This paper will first theoretically analyze GANs' approximation property. Similar to the universal approximation property of the fully connected neural networks with one hidden layer, we prove that the generator with the input latent variable in GANs can universally approximate the potential data distribution given the increasing hidden neurons. Furthermore, we propose an approach named stochastic data generation (SDG) to enhance GANs'approximation ability. Our approach is based on the simple idea of imposing randomness through data generation in GANs by a prior distribution on the conditional probability between the layers. SDG approach can be easily implemented by using the reparameterization trick. The experimental results on synthetic dataset verify the improved approximation ability obtained by this SDG approach. In the practical dataset, four GANs using SDG can also outperform the corresponding traditional GANs when the model architectures are smaller.
