Stable Training of Normalizing Flows for High-dimensional Variational Inference

arXiv:2402.16408v1 Announce Type: cross
Abstract: Variational inference with normalizing flows (NFs) is an increasingly popular alternative to MCMC methods. In particular, NFs based on coupling layers (Real NVPs) are frequently used due to their good empirical performance. In theory, increasing the depth of normalizing flows should lead to more accurate posterior approximations. However, in practice, training deep normalizing flows for approximating high-dimensional posterior distributions is often infeasible due to the high variance of the stochastic gradients. In this work, we …

abstract arxiv cs.lg good inference mcmc nfs performance popular posterior stat.ml theory training type