Learning structural weight uncertainty for sequential decision-making

Ruiyi Zhang, Chunyuan Li, Changyou Chen, Lawrence Carin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Scopus citations


Learning probability distributions on the weights of neural networks (NNs) has recently proven beneficial in many applications. Bayesian methods, such as Stein variational gradient descent (SVGD), offer an elegant framework to reason about NN model uncertainty. However, by assuming independent Gaussian priors for the individual NN weights (as often applied), SVGD does not impose prior knowledge that there is often structural information (dependence) among weights. We propose efficient posterior learning of structural weight uncertainty, within an SVGD framework, by employing matrix variate Gaussian priors on NN parameters. We further investigate the learned structural uncertainty in sequential decisionmaking problems, including contextual bandits and reinforcement learning. Experiments on several synthetic and real datasets indicate the superiority of our model, compared with state-of-the-art methods.
Original languageEnglish (US)
Title of host publicationInternational Conference on Artificial Intelligence and Statistics, AISTATS 2018
Number of pages10
StatePublished - Jan 1 2018
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2021-02-09


Dive into the research topics of 'Learning structural weight uncertainty for sequential decision-making'. Together they form a unique fingerprint.

Cite this