Generative Adversarial Networks (GANs) have been impactful on many problems and applications but suffer from unstable training. The Wasserstein GAN (WGAN) leverages the Wasserstein distance to avoid the caveats in the minmax two-player training of GANs but has other defects such as mode collapse and lack of metric to detect the convergence. We introduce a novel inferential Wasserstein GAN (iWGAN) model, which is a principled framework to fuse auto-encoders and WGANs. The iWGAN model jointly learns an encoder network and a generator network motivated by the iterative primal dual optimization process. The encoder network maps the observed samples to the latent space and the generator network maps the samples from the latent space to the data space. We establish the generalization error bound of the iWGAN to theoretically justify its performance. We further provide a rigorous probabilistic interpretation of our model under the framework of maximum likelihood estimation. The iWGAN, with a clear stopping criteria, has many advantages over other autoencoder GANs. The empirical experiments show that the iWGAN greatly mitigates the symptom of mode collapse, speeds up the convergence, and is able to provide a measurement of quality check for each individual sample. We illustrate the ability of the iWGAN by obtaining competitive and stable performances for benchmark datasets.
翻译:瓦塞斯特因GAN(WGAN)利用瓦塞斯特因距离来避免GANS二人训练的隐形双球员训练中的警告,但也存在其他缺陷,例如模式崩溃和缺乏检测趋同的度量等。我们引入了一个新的推论瓦塞尔斯坦GAN(iWGAN)模型,这是连接自动编码器和WGANs的一个原则框架。iWGAN模型联合学习了一个编码器网络和发电机网络,其动机是迭代初线双优化程序。编码网络将观测到的样品绘制到潜在的空间,而发电机网络则将样品从潜在空间绘制到数据空间。我们确定iWGAN(iWGAN)的概括性差,以便从理论上证明其性能的合理性能。我们还在最大可能性估计的框架内对我们的模型作了严格的概率解释。iWGAN(具有明确的停止标准)与其他自动编码网络相比,有许多优势。我们通过实验性能性能的测试能力来降低iWG(iWG)的稳定性,从而大大降低单个数据趋同速度。