Oleg Arenz, Mingjun Zhong, Gerhard Neumann

Accepted at JMLR

Many methods for machine learning rely on approximate inference from intractable probability distributions. Variational inference approximates such distributions by tractable models that can be subsequently used for approximate inference. Learning sufficiently accurate approximations requires a rich model family and careful exploration of the relevant modes of the target distribution. We propose a method for learning accurate GMM approximations of intractable probability distributions based on insights from policy search by using information-geometric trust regions for principled exploration. For efficient improvement of the GMM approximation, we derive a lower bound on the corresponding optimization objective enabling us to update the components independently. This journal paper is an extension of the ICML 2018 paper "Efficient-Gradient Free Variational Inference by Policy Search" with better sample complexity, more detailed analysis and more experiments. 

Source Code: https://github.com/OlegArenz/VIPS

Pre-Print: https://arxiv.org/abs/1907.04710