English

Multi-group Gaussian Processes

Methodology 2021-10-19 v1 Applications

Abstract

Gaussian processes (GPs) are pervasive in functional data analysis, machine learning, and spatial statistics for modeling complex dependencies. Modern scientific data sets are typically heterogeneous and often contain multiple known discrete subgroups of samples. For example, in genomics applications samples may be grouped according to tissue type or drug exposure. In the modeling process it is desirable to leverage the similarity among groups while accounting for differences between them. While a substantial literature exists for GPs over Euclidean domains Rp\mathbb{R}^p, GPs on domains suitable for multi-group data remain less explored. Here, we develop a multi-group Gaussian process (MGGP), which we define on Rp×C\mathbb{R}^p\times \mathscr{C}, where C\mathscr{C} is a finite set representing the group label. We provide general methods to construct valid (positive definite) covariance functions on this domain, and we describe algorithms for inference, estimation, and prediction. We perform simulation experiments and apply MGGP to gene expression data to illustrate the behavior and advantages of the MGGP in the joint modeling of continuous and categorical variables.

Keywords

Cite

@article{arxiv.2110.08411,
  title  = {Multi-group Gaussian Processes},
  author = {Didong Li and Andrew Jones and Sudipto Banerjee and Barbara E. Engelhardt},
  journal= {arXiv preprint arXiv:2110.08411},
  year   = {2021}
}