论文标题
离散索引流
Discretely Indexed Flows
论文作者
论文摘要
在本文中，我们提出离散索引流（DIF）作为解决变异估计问题的新工具。粗略地说，DIF是作为标准化流（NF）的扩展而建立的，其中确定性运输变得随机运输，并且更精确地索引了索引。由于基础附加潜在变量的离散性质，DIF继承了NF的良好计算行为：它们受益于可拖动密度和直接采样方案，因此可以用于变量推理（VI）的双重问题（VI）和变量密度估计（VDE）。另一方面，DIF也可以理解为混合密度模型的扩展，其中恒定混合物的重量被柔性功能所取代。结果，DIF更适合捕获不连续性，尖锐边缘和细节的分布，这是该结构的主要优势。最后，我们提出了一种实践中构造dif的方法，并看到可以顺序级联的DIF，并用NF级联。
In this paper we propose Discretely Indexed flows (DIF) as a new tool for solving variational estimation problems. Roughly speaking, DIF are built as an extension of Normalizing Flows (NF), in which the deterministic transport becomes stochastic, and more precisely discretely indexed. Due to the discrete nature of the underlying additional latent variable, DIF inherit the good computational behavior of NF: they benefit from both a tractable density as well as a straightforward sampling scheme, and can thus be used for the dual problems of Variational Inference (VI) and of Variational density estimation (VDE). On the other hand, DIF can also be understood as an extension of mixture density models, in which the constant mixture weights are replaced by flexible functions. As a consequence, DIF are better suited for capturing distributions with discontinuities, sharp edges and fine details, which is a main advantage of this construction. Finally we propose a methodology for constructiong DIF in practice, and see that DIF can be sequentially cascaded, and cascaded with NF.
