Efficient Gradient-Free Variational Inference using Policy Search

Arenz, O., Zhong, M. and Neumann, Gerhard (2018) Efficient Gradient-Free Variational Inference using Policy Search. In: Proceedings of the International Conference on Machine Learning.

Efficient Gradient-Free Variational Inference using Policy Search
VIPS_and_supplement.pdf - Whole Document

Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive


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, Policy Search, Mixture of Gaussians
Subjects:G Mathematical and Computer Sciences > G760 Machine Learning
Divisions:College of Science > School of Computer Science
ID Code:32456
Deposited On:20 Oct 2018 21:30

Repository Staff Only: item control page