vix.ing · top · new · best · stats · spec

Two Methods For Wild Variational Inference

2016/11/30 by Qiang Liu, Liu, Qiang, Yihao Feng +1 · 3 citations
Computer Science · Physics and Astronomy · Mathematics · #Gaussian Processes and Bayesian Inference #Model Reduction and Neural Networks #Markov Chains and Monte Carlo Methods

paper · pdf · doi:10.48550/arxiv.1612.00081

Abstract

Variational inference provides a powerful tool for approximate probabilistic in- ference on complex, structured models. Typical variational inference methods, however, require to use inference networks with computationally tractable proba- bility density functions. This largely limits the design and implementation of vari- ational inference methods. We consider wild variational inference methods that do not require tractable density functions on the inference networks, and hence can be applied in more challenging cases. As an example of application, we treat stochastic gradient Langevin dynamics (SGLD) as an inference network, and use our methods to automatically adjust the step sizes of SGLD, yielding significant improvement over the hand-designed step size schemes

Citations

Cited by

Related