Home

Awesome

AugmentedGaussianProcesses.jl

This package is being deprecated in favor of the JuliaGaussianProcesses ecosystem. In particular most of the features of augmentations is being moved to a new package called AugmentedGPLikelihoods.jl. It is still a work in progress though.

Docs Latest Docs Stable CI Coverage Status DOI

AugmentedGaussianProcesses.jl is a Julia package in development for Data Augmented Sparse Gaussian Processes. It contains a collection of models for different gaussian and non-gaussian likelihoods, which are transformed via data augmentation into conditionally conjugate likelihood allowing for extremely fast inference via block coordinate updates. There are also more options to use more traditional variational inference via quadrature or Monte Carlo integration.

The theory for the augmentation is given in the following paper : Automated Augmented Conjugate Inference for Non-conjugate Gaussian Process Models

You can also use the package in Python via PyJulia!

Packages models :

Two GP classification likelihoods

<p align=center> <img src="docs/src/assets/Classification.png"> </p>

Four GP Regression likelihoods

<p align=center> <img src="docs/src/assets/Regression.png"> </p>

Two GP event counting likelihoods

<p align=center> <img src="docs/src/assets/Events.png"> </p>

One Multi-Class Classification Likelihood

<p align=center> <img src="docs/src/assets/final3D.png" width=400px> </p>

Multi-Ouput models

More models in development

Install the package

The package requires at least Julia 1.3 Run julia, press ] and type add AugmentedGaussianProcesses, it will install the package and all its dependencies.

Use the package

A complete documentation is available in the docs. For a short start now you can use this very basic example where X_train is a matrix N x D where N is the number of training points and D is the number of dimensions and Y_train is a vector of outputs (or matrix of independent outputs).

using AugmentedGaussianProcesses;
using KernelFunctions
model = SVGP(SqExponentialKernel(), LogisticLikelihood(), AnalyticSVI(100), 64)
train!(model, X_train, Y_train, 100)
Y_predic = predict_y(model, X_test) # For getting the label directly
Y_predic_prob, Y_predic_prob_var = proba_y(model, X_test) # For getting the likelihood (and likelihood uncertainty) of predicting class 1

Both documentation and examples/tutorials are available.

References :

Check out my website for more news

"Gaussian Processes for Machine Learning" by Carl Edward Rasmussen and Christopher K.I. Williams

AISTATS 20' "Automated Augmented Conjugate Inference for Non-conjugate Gaussian Process Models" by Théo Galy-Fajou, Florian Wenzel and Manfred Opper [https://arxiv.org/abs/2002.11451][autoconj]

UAI 19' "Multi-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation" by Théo Galy-Fajou, Florian Wenzel, Christian Donner and Manfred Opper https://arxiv.org/abs/1905.09670

ECML 17' "Bayesian Nonlinear Support Vector Machines for Big Data" by Florian Wenzel, Théo Galy-Fajou, Matthäus Deutsch and Marius Kloft. https://arxiv.org/abs/1707.05532

AAAI 19' "Efficient Gaussian Process Classification using Polya-Gamma Variables" by Florian Wenzel, Théo Galy-Fajou, Christian Donner, Marius Kloft and Manfred Opper. https://arxiv.org/abs/1802.06383

NeurIPS 18' "Moreno-Muñoz, Pablo, Antonio Artés, and Mauricio Álvarez. "Heterogeneous multi-output Gaussian process prediction." Advances in Neural Information Processing Systems. 2018." [https://papers.nips.cc/paper/7905-heterogeneous-multi-output-gaussian-process-prediction][neuripsmultiouput]

UAI 13' "Gaussian Process for Big Data" by James Hensman, Nicolo Fusi and Neil D. Lawrence https://arxiv.org/abs/1309.6835

JMLR 11' "Robust Gaussian process regression with a Student-t likelihood." by Jylänki Pasi, Jarno Vanhatalo, and Aki Vehtari. http://www.jmlr.org/papers/v12/jylanki11a.html