Spectral Mixture Kernels for Multi-Output Gaussian Processes

TL;DR

This paper introduces a new family of spectral mixture kernels for multi-output Gaussian processes that are more expressive and interpretable, capable of modeling delays and phase differences across channels.

Contribution

It extends spectral mixture kernels to multivariate cases using Cramér's Theorem, enabling more expressive and interpretable multi-output Gaussian process models.

Findings

The proposed kernels effectively model delays and phase differences.

Validated on synthetic data with promising results.

Outperforms existing methods on real-world datasets.

Abstract

Early approaches to multiple-output Gaussian processes (MOGPs) relied on linear combinations of independent, latent, single-output Gaussian processes (GPs). This resulted in cross-covariance functions with limited parametric interpretation, thus conflicting with the ability of single-output GPs to understand lengthscales, frequencies and magnitudes to name a few. On the contrary, current approaches to MOGP are able to better interpret the relationship between different channels by directly modelling the cross-covariances as a spectral mixture kernel with a phase shift. We extend this rationale and propose a parametric family of complex-valued cross-spectral densities and then build on Cram\'er's Theorem (the multivariate version of Bochner's Theorem) to provide a principled approach to design multivariate covariance functions. The so-constructed kernels are able to model delays among channels in addition to phase differences and are thus more expressive than previous methods, while also providing full parametric interpretation of the relationship across channels. The proposed method is first validated on synthetic data and then compared to existing MOGP methods on two real-world examples.