Sampling the Variational Posterior with Local Refinement.
Authors
Havasi, Marton
Snoek, Jasper
Tran, Dustin
Gordon, Jonathan
Hernández-Lobato, José Miguel
Publication Date
2021-11-08Journal Title
Entropy (Basel)
ISSN
1099-4300
Publisher
MDPI AG
Volume
23
Issue
11
Language
en
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Havasi, M., Snoek, J., Tran, D., Gordon, J., & Hernández-Lobato, J. M. (2021). Sampling the Variational Posterior with Local Refinement.. Entropy (Basel), 23 (11) https://doi.org/10.3390/e23111475
Abstract
Variational inference is an optimization-based method for approximating the posterior distribution of the parameters in Bayesian probabilistic models. A key challenge of variational inference is to approximate the posterior with a distribution that is computationally tractable yet sufficiently expressive. We propose a novel method for generating samples from a highly flexible variational approximation. The method starts with a coarse initial approximation and generates samples by refining it in selected, local regions. This allows the samples to capture dependencies and multi-modality in the posterior, even when these are absent from the initial approximation. We demonstrate theoretically that our method always improves the quality of the approximation (as measured by the evidence lower bound). In experiments, our method consistently outperforms recent variational inference methods in terms of log-likelihood and ELBO across three example tasks: the Eight-Schools example (an inference task in a hierarchical model), training a ResNet-20 (Bayesian inference in a large neural network), and the Mushroom task (posterior sampling in a contextual bandit problem).
Keywords
bayesian inference, variational inference, deep neural networks, contextual bandits
Identifiers
External DOI: https://doi.org/10.3390/e23111475
This record's URL: https://www.repository.cam.ac.uk/handle/1810/330598
Rights
Licence:
https://creativecommons.org/licenses/by/4.0/
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.