GPyTorch (Beta Release)
News!
- The Beta release is currently out! Note that it requires the PyTorch preview build (pytorch-nightly, >= 1.0).
- If you need to install the alpha release (we recommend you use the latest version though!), check out the alpha release.
GPyTorch is a Gaussian process library implemented using PyTorch. GPyTorch is designed for creating scalable, flexible, and modular Gaussian process models with ease.
Internally, GPyTorch differs from many existing approaches to GP inference by performing all inference operations using modern numerical linear algebra techniques like preconditioned conjugate gradients. Implementing a scalable GP method is as simple as providing a matrix multiplication routine with the kernel matrix and its derivative via our LazyTensor
interface, or by composing many of our already existing LazyTensors
. This allows not only for easy implementation of popular scalable GP techniques, but often also for significantly improved utilization of GPU computing compared to solvers based on the Cholesky decomposition.
GPyTorch provides (1) significant GPU acceleration (through MVM based inference); (2) state-of-the-art implementations of the latest algorithmic advances for scalability and flexibility (SKI/KISS-GP, stochastic Lanczos expansions, LOVE, SKIP, stochastic variational deep kernel learning, ...); (3) easy integration with deep learning frameworks.
Examples and Tutorials
Right now, the package is in alpha release, and while we believe that the interface is reasonably stable, things may change. For now, see our numerous examples and tutorials on how to construct all sorts of models in GPyTorch. These example notebooks and a walk through of GPyTorch are also available at our ReadTheDocs page here
Installation
Requirements:
- Python >= 3.6
- PyTorch >= 1.0
N.B. GPyTorch will not run on PyTorch 0.4.1 or earlier versions.
The easiest way to install GPyTorch is by installing the nightly PyTorch build (pytorch-nightly >= 1.0.0
) using the appropriate command from here.
Then install GPyTorch using pip:
pip install gpytorch
To use packages globally but install GPyTorch as a user-only package, use pip install --user
above.
Latest (unstable) version
To get the latest (unstable) version, run
pip install git+https://github.com/cornellius-gp/gpytorch.git
Citing Us
If you use GPyTorch, please cite the following papers:
@inproceedings{gardner2018gpytorch,
title={
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration},
author={Gardner, Jacob R and Pleiss, Geoff and Bindel, David and Weinberger, Kilian Q and Wilson, Andrew Gordon},
booktitle={NIPS},
year={2018}
}
Documentation
- For tutorials and examples, check out the examples folder.
- For in-depth documentation, check out our read the docs.
Development
To run the unit tests:
python -m unittest
By default, the random seeds are locked down for some of the tests. If you want to run the tests without locking down the seed, run
UNLOCK_SEED=true python -m unittest
Please lint the code with flake8
.
pip install flake8 # if not already installed
flake8
Founding Team
GPyTorch is developed at Cornell University by
- Jake Gardner (lead developer)
- Geoff Pleiss (lead developer)
- Kilian Weinberger
- Andrew Gordon Wilson
- Max Balandat
- Eytan Bakshy
- David Arbour
We would like to thank our other contributors including (but not limited to) Ruihan Wu, Bram Wallace, Sam Stanton, and Jared Frank.
Acknowledgements
Development of GPyTorch is supported by funding from Facebook and the Bill and Melinda Gates Foundation.