Multi-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation
Théo Galy-Fajou, Florian Wenzel, Christian Donner, Manfred Opper
Abstract
We propose a new scalable multi-class Gaussian process classification approach building on a novel modified softmax likelihood function. The new likelihood has two benefits: it leads to well-calibrated uncertainty estimates and allows for an efficient latent variable augmentation. The augmented model has the advantage that it is conditionally conjugate leading to a fast variational inference method via block coordinate ascent updates. Previous approaches suffered from a trade-off between uncertainty calibration and speed. Our experiments show that our method leads to well-calibrated uncertainty estimates and competitive predictive performance while being up to two orders faster than the state of the art.
BibTeX
@InProceedings{pmlr-v115-galy-fajou20a,
title = {Multi-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation},
author = {Galy-Fajou, Th{\'{e}}o and Wenzel, Florian and Donner, Christian and Opper, Manfred},
booktitle = {Proceedings of The 35th Uncertainty in Artificial Intelligence Conference},
pages = {755--765},
year = {2020},
editor = {Adams, Ryan P. and Gogate, Vibhav},
volume = {115},
series = {Proceedings of Machine Learning Research},
month = {22--25 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v115/galy-fajou20a/galy-fajou20a.pdf},
url = {https://proceedings.mlr.press/v115/galy-fajou20a.html},
abstract = {We propose a new scalable multi-class Gaussian process classification approach building on a novel modified softmax likelihood function. The new likelihood has two benefits: it leads to well-calibrated uncertainty estimates and allows for an efficient latent variable augmentation. The augmented model has the advantage that it is conditionally conjugate leading to a fast variational inference method via block coordinate ascent updates. Previous approaches suffered from a trade-off between uncertainty calibration and speed. Our experiments show that our method leads to well-calibrated uncertainty estimates and competitive predictive performance while being up to two orders faster than the state of the art.}
}