Efficient Gradient-Free Variational Inference using Policy Search

Arenz, Oleg and Neumann, Gerhard and Zhong, Mingjun (2018) Efficient Gradient-Free Variational Inference using Policy Search. Proceedings of the 35th International Conference on Machine Learning, 80 . pp. 234-243. ISSN 1938-7228

Full content URL: http://proceedings.mlr.press/v80/arenz18a/arenz18a...

Documents
arenz18a.pdf
[img]
[Download]
[img] PDF
arenz18a.pdf - Whole Document

3MB
Item Type:Article
Item Status:Live Archive

Abstract

Inference from complex distributions is a common problem in machine learning needed for many Bayesian methods. We propose an efficient, gradient-free method for learning general GMM approximations of multimodal distributions based on recent insights from stochastic search methods. Our method establishes information-geometric trust regions to ensure efficient exploration of the sampling space and stability of the GMM updates, allowing for efficient estimation of multi-variate Gaussian variational distributions. For GMMs, we apply a variational lower bound to decompose the learning objective into sub-problems given by learning the individual mixture components and the coefficients. The number of mixture components is adapted online in order to allow for arbitrary exact approximations. We demonstrate on several domains that we can learn significantly better approximations than competing variational inference methods and that the quality of samples drawn from our approximations is on par with samples created by state-of-the-art MCMC samplers that require significantly more computational resources.

Keywords:Variational Inference, Reinforcement learning
Subjects:G Mathematical and Computer Sciences > G760 Machine Learning
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:33871
Deposited On:25 Oct 2018 12:39

Repository Staff Only: item control page