We propose a simple and scalable method for improving the flexibility of variational inference through a transformation with autoregressive networks. Autoregressive networks, such as RNNs and MADE, are very powerful models; however, ancestral sampling in such networks is a sequential operation, therefore unappealing for direct use as approximate posteriors in variational inference on parallel hardware such as GPUs. We find that by inverting autoregressive networks we can obtain equally powerful data transformations that can often be computed in parallel. We show that such data transformations, inverse autoregressive flows (IAF), can be used to transform a simple distribution over the latent variables into a much more flexible distribution, while still allowing us to compute the resulting variables' probability density function. The method is simple to implement, can be made arbitrarily flexible, and (in contrast with previous work) is naturally applicable to latent variables that are organized in multidimensional tensors, such as 2D grids or time series. The method is applied to a novel deep architecture of variational auto-encoders. In experiments we demonstrate that autoregressive flow leads to significant performance gains when applied to variational autoencoders for natural images.

本文提出了一种新型正则化流架构——逆自回归流，它是一种基于自回归神经网络的可逆转换链。实验结果表明，逆自回归流显著改善了高维空间中对角高斯近似后验的变分推断，同时也证明了，结合逆自回归流的新型变分自编码器，在自然图像的对数似然度方面，与神经自回归模型相当，同时合成速度显著更快。

逆自回归流提高变分推断