https://github.com/t-vi/candlegp

Gaussian Processes in Pytorch
https://github.com/t-vi/candlegp

Last synced: about 1 month ago
JSON representation

Gaussian Processes in Pytorch

• Host: GitHub
• URL: https://github.com/t-vi/candlegp
• Owner: t-vi
• License: apache-2.0
• Created: 2017-10-23T20:45:51.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2020-02-26T16:38:00.000Z (almost 5 years ago)
• Last Synced: 2024-11-14T05:33:49.651Z (about 2 months ago)
• Language: Jupyter Notebook
• Size: 2.62 MB
• Stars: 74
• Watchers: 3
• Forks: 8
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-pytorch-list-CNVersion - candlegp
• Awesome-pytorch-list - candlegp

README

        
# CandleGP - Gaussian Processes in Pytorch

*Thomas Viehmann*, [email protected]

*Note:* This stems from before the Tensor/Variable merge, so it is really old.

I recently needed bits and ported those to PyTorch 1.4, but there are rough edges w.r.t. dimensionality of quantities and there will be unported bits.

I felt Bayesian the other day, so I ported (a tiny part of) the

excellent [GPFlow library](https://github.com/gpflow/gpflow) to

Pytorch.

I have kept the structure close to GPFlow.

Most of the great ideas are from the GPFlow team, errors are my own.

The functionality is demonstrated by the following notebooks

adapted from gpflow:

- [Classification example](notebooks/classification.ipynb)

- [Regression example](notebooks/gp_regression.ipynb)

- [Markov Chain Monte Carlo for non-gaussian likelihoods](notebooks/mcmc.ipynb)

- [Upper bound for variational inference](notebooks/upper_bound.ipynb)

- [SVGP with minibatch training](notebooks/minibatches.ipynb)

- [Multi-class classification](notebooks/multiclass.ipynb)

Todo:

- GPLVM