Convolutional Normalizing Flows for Deep Gaussian Processes
Abstract
Deep Gaussian processes (DGPs), a hierarchical composition of GP models, have successfully boosted the expressive power of their single-layer counterpart. However, it is impossible to perform exact inference in DGPs, which has motivated the recent development of variational inference-based methods. Unfortunately, either these methods yield a biased posterior belief or it is difficult to evaluate their convergence. This paper introduces a new approach for specifying flexible, arbitrarily complex, and scalable approximate posterior distributions. The posterior distribution is constructed through a normalizing flow (NF) which transforms a simple initial probability into a more complex one through a sequence of invertible transformations. Moreover, a novel convolutional normalizing flow (CNF) is developed to improve the time efficiency and capture dependency between layers. Empirical evaluation shows that CNF DGP outperforms the state-of-the-art approximation methods for DGPs.
Keywords
Cite
@article{arxiv.2104.08472,
title = {Convolutional Normalizing Flows for Deep Gaussian Processes},
author = {Haibin Yu and Dapeng Liu and Yizhou Chen and Bryan Kian Hsiang Low and Patrick Jaillet},
journal= {arXiv preprint arXiv:2104.08472},
year = {2021}
}
Comments
To appear in Proceedings of the International Joint Conference on Neural Networks 2021 (IJCNN'21). arXiv admin note: text overlap with arXiv:1910.11998