Incremental Kernel Principal Components Subspace Inference With Nyström Approximation for Bayesian Deep Learning

Incremental Kernel Principal Components Subspace Inference With Nyström Approximation for Bayesian Deep Learning

As the state-of-the-art technology of Bayesian inference, based on low-dimensional principal components analysis (PCA) subspace inference methods can provide approximately accurate predictive distribution and well calibrated uncertainty. However, the main problem of PCA method is that it is a linear...

Full description

Bibliographic Details
Main Authors: Yongguang Wang, Shuzhen Yao, Tian Xu
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Bayesian deep learning
incremental kernel PCA
elliptical slice sampling
variational inference
Nyström approximation
Online Access:https://ieeexplore.ieee.org/document/9364973/

Internet

https://ieeexplore.ieee.org/document/9364973/

Similar Items