Representation learning seeks to expose certain aspects of observed data in a
learned representation that's amenable to downstream tasks like classification.
For instance, a good representation for 2D images might be one that describes
only global structure and discards information about detailed texture. In this
paper, we present a simple but principled method to learn such global
representations by combining Variational Autoencoder (VAE) with neural
autoregressive models such as RNN, MADE and PixelRNN/CNN. Our proposed VAE
model allows us to have control over what the global latent code can learn and
, by designing the architecture accordingly, we can force the global latent
code to discard irrelevant information such as texture in 2D images, and hence
the VAE only "autoencodes" data in a lossy fashion. In addition, by leveraging
autoregressive models as both prior distribution $p(z)$ and decoding
distribution $p(x|z)$, we can greatly improve generative modeling performance
of VAEs, achieving new state-of-the-art results on MNIST, OMNIGLOT and
Caltech-101 Silhouettes density estimation tasks.

本文提出了一种基于变分自编码器和神经自回归模型的简单但原则性的方法来学习全局表示，该方法允许对全局潜在特征进行控制，通过设计相应的架构，可以迫使全局潜在特征丢弃 2D 图像纹理等无关信息，并且通过利用自回归模型作为潜在分布和解码分布，可以大大提高 VAE 的生成建模性能，实现了 MNIST、OMNIGLOT 和 Caltech-101 Silhouettes 密度估计任务的新的最先进结果。