论文标题
任意条件的后匹配
Posterior Matching for Arbitrary Conditioning
论文作者
论文摘要
任意条件是无监督的学习中的一个重要问题，我们试图建模有条件的密度$ p（\ mathbf {x} _u \ mid \ mathbf {x} _o）$，对于所有可能的非交流子集$ o，u \ subset $，u \ subset \ subset \ sebset \ sebSet \ {1，\ dots，dots，d \} $。但是，绝大多数密度估计仅着重于建模关节分布$ p（\ mathbf {x}）$，其中特征之间的重要条件依赖性是不透明的。我们提出了一个简单而通用的框架，即后匹配，使变异自动编码器（VAE）能够执行任意调节，而无需对VAE本身进行修改。后匹配适用于用于接头密度估计的众多现有基于VAE的方法，从而规定了以前的任意条件方法所需的专门模型。我们发现，对于具有各种VAE的各种任务（例如〜离散，分层，vade），后匹配与当前的最新方法相当或优越。
Arbitrary conditioning is an important problem in unsupervised learning, where we seek to model the conditional densities $p(\mathbf{x}_u \mid \mathbf{x}_o)$ that underly some data, for all possible non-intersecting subsets $o, u \subset \{1, \dots , d\}$. However, the vast majority of density estimation only focuses on modeling the joint distribution $p(\mathbf{x})$, in which important conditional dependencies between features are opaque. We propose a simple and general framework, coined Posterior Matching, that enables Variational Autoencoders (VAEs) to perform arbitrary conditioning, without modification to the VAE itself. Posterior Matching applies to the numerous existing VAE-based approaches to joint density estimation, thereby circumventing the specialized models required by previous approaches to arbitrary conditioning. We find that Posterior Matching is comparable or superior to current state-of-the-art methods for a variety of tasks with an assortment of VAEs (e.g.~discrete, hierarchical, VaDE).
