Christopher Wolf, Maximilian Karl, Patrick van der Smagt
TL;DR本研究提出了一种使用 Hamiltonian Monte Carlo 算法中的 MCMC 步骤来改善后验分布逼近的方法,并通过实验结果证明了这种方法的理论优势和性能改进。
Abstract
variational inference lies at the core of many state-of-the-art algorithms.
To improve the approximation of the posterior beyond parametric families, it
was proposed to include mcmc steps into the variational low