论文标题
关于VAE的教程：从贝叶斯的规则到无损压缩
A Tutorial on VAEs: From Bayes' Rule to Lossless Compression
论文作者
论文摘要
变性自动编码器（VAE）是一个简单，高效且流行的深度最大似然模型。尽管对VAE的使用是广泛的，但VAE的推导并没有广泛理解。在本教程中，我们将通过VAE目标的各种推导和解释来概述VAE和游览。从概率的角度来看，我们将通过贝叶斯的规则，重要性采样和变化量的公式来检查VAE。从信息理论的角度来看，我们将通过噪声通道的无损压缩和传播的镜头检查VAE。然后，我们将确定对VAE配方及其实际后果的两个共同误解。最后，我们将使用代码示例（随附的Jupyter笔记本）在玩具2D数据上可视化VAE的功能和局限性。
The Variational Auto-Encoder (VAE) is a simple, efficient, and popular deep maximum likelihood model. Though usage of VAEs is widespread, the derivation of the VAE is not as widely understood. In this tutorial, we will provide an overview of the VAE and a tour through various derivations and interpretations of the VAE objective. From a probabilistic standpoint, we will examine the VAE through the lens of Bayes' Rule, importance sampling, and the change-of-variables formula. From an information theoretic standpoint, we will examine the VAE through the lens of lossless compression and transmission through a noisy channel. We will then identify two common misconceptions over the VAE formulation and their practical consequences. Finally, we will visualize the capabilities and limitations of VAEs using a code example (with an accompanying Jupyter notebook) on toy 2D data.
