TL;DR本文提出了基于 Quasi-Monte Carlo 采样的方差减少方法,有效地提高了 Monte Carlo gradient estimator 的 MCVI 性能,并通过实验验证了该方法。
Abstract
Many machine learning problems involve monte carlo gradient estimators. As a
prominent example, we focus on monte carlo variational inference (MCVI) in this
paper. The performance of MCVI crucially depends on the