论文标题
连续归一化流的路径梯度估计器
Path-Gradient Estimators for Continuous Normalizing Flows
论文作者
论文摘要
最近的工作已经为简单的高斯分布建立了一个路径梯度估计器，并认为该路径梯度在变化分布接近确切目标分布的状态下尤其有益。但是，在许多应用中，这种制度无法通过简单的高斯分布来达到。在这项工作中，我们通过提出一个途径梯度估计量来克服这一关键限制，以使连续归一化流的相当表现力的变异家族更加表现力。我们概述了一种有效的算法来计算该估计器并通过经验建立出色的性能。
Recent work has established a path-gradient estimator for simple variational Gaussian distributions and has argued that the path-gradient is particularly beneficial in the regime in which the variational distribution approaches the exact target distribution. In many applications, this regime can however not be reached by a simple Gaussian variational distribution. In this work, we overcome this crucial limitation by proposing a path-gradient estimator for the considerably more expressive variational family of continuous normalizing flows. We outline an efficient algorithm to calculate this estimator and establish its superior performance empirically.
