Scalable Gaussian Process Separation for Kernels with a Non-Stationary Phase
Jan Graßhoff, Alexandra Jankowski, Philipp Rostalski
Abstract
The application of Gaussian processes (GPs) to large data sets is limited due to heavy memory and computational requirements. A variety of methods has been proposed to enable scalability, one of which is to exploit structure in the kernel matrix. Previous methods, however, cannot easily deal with mixtures of non-stationary processes. This paper investigates an efficient GP framework, that extends structured kernel interpolation methods to GPs with a non-stationary phase. We particularly treat the separation of nonstationary sources, which is a problem that commonly arises e.g. in spatio-temporal biomedical datasets. Our approach employs multiple sets of non-equidistant inducing points to account for the non-stationarity and retrieve Toeplitz and Kronecker structure in the kernel matrix allowing for efficient inference and kernel learning. Our approach is demonstrated on numerical examples and large spatio-temporal biomedical problems.
BibTeX
@InProceedings{pmlr-v119-grasshoff20a,
title = {Scalable {G}aussian Process Separation for Kernels with a Non-Stationary Phase},
author = {Gra{\ss}hoff, Jan and Jankowski, Alexandra and Rostalski, Philipp},
booktitle = {Proceedings of the 37th International Conference on Machine Learning},
pages = {3722--3731},
year = {2020},
editor = {III, Hal Daumé and Singh, Aarti},
volume = {119},
series = {Proceedings of Machine Learning Research},
month = {13--18 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v119/grasshoff20a/grasshoff20a.pdf},
url = {https://proceedings.mlr.press/v119/grasshoff20a.html},
abstract = {The application of Gaussian processes (GPs) to large data sets is limited due to heavy memory and computational requirements. A variety of methods has been proposed to enable scalability, one of which is to exploit structure in the kernel matrix. Previous methods, however, cannot easily deal with mixtures of non-stationary processes. This paper investigates an efficient GP framework, that extends structured kernel interpolation methods to GPs with a non-stationary phase. We particularly treat the separation of nonstationary sources, which is a problem that commonly arises e.g. in spatio-temporal biomedical datasets. Our approach employs multiple sets of non-equidistant inducing points to account for the non-stationarity and retrieve Toeplitz and Kronecker structure in the kernel matrix allowing for efficient inference and kernel learning. Our approach is demonstrated on numerical examples and large spatio-temporal biomedical problems.}
}