Sparse Orthogonal Variational Inference for Gaussian Processes

Jiaxin Shi, Michalis K. Titsias, and Andriy Mnih, AISTATS 2020. https://arxiv.org/abs/1910.10596

Code for reproducing the animation:

solvegp.ipynb

Deep Convolutional Gaussian Processes for CIFAR10 Classification

Thanks to Shengyang Sun @ssydasheng who reproduced the experiments in https://github.com/ssydasheng/Harmonic-Kernel-Decomposition/blob/master/exp/classification.py, where setting the --method option to sovgd corresponds to SOLVE-GP (The setting is slightly different from the original paper with comparable results). Also see the accompanying paper for our latest development that leads to even better results.

Tensorflow >= 1.4
GPflow == 1.5.1

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
data/snelson		data/snelson
results		results
.gitignore		.gitignore
README.md		README.md
solvegp.ipynb		solvegp.ipynb