Given an unnormalized target distribution we want to obtain approximate
samples from it and a tight lower bound on its (log) normalization constant log
Z. Annealed Importance Sampling (AIS) with Hamiltonian MCMC is a powerful
method that can be used to do this. Its main drawback is that it uses
non-differentiable transition kernels, which makes tuning its many parameters
hard. We propose a framework to use an AIS-like procedure with Uncorrected
Hamiltonian MCMC, called Uncorrected Hamiltonian Annealing. Our method leads to
tight and differentiable lower bounds on log Z. We show empirically that our
method yields better performances than other competing approaches, and that the
ability to tune its parameters using reparameterization gradients may lead to
large performance improvements.

提出了一种使用类似于 AIS（Annealed Importance Sampling）的 Uncorrected Hamiltonian MCMC 过程的框架，称为 Uncorrected Hamiltonian Annealing，它能够在获得近似样本的同时，获得一个紧致、可微分的 logZ 的下界，相比其他竞争方法，我们的方法表现更好，并且使用重新参数化梯度调整参数能够显著提高性能。