Deep Gaussian Processes for Functional Maps

TL;DR

This paper introduces Deep Gaussian Processes for Functional Maps (DGPFM), a novel method that models complex nonlinear relationships in function space with improved uncertainty quantification, scalable inference, and broad applicability.

Contribution

The paper proposes a flexible DGPFM framework that integrates kernel integral transforms, nonlinear activations, and scalable variational inference for functional data analysis.

Findings

DGPFM outperforms existing methods in predictive accuracy.

DGPFM provides well-calibrated uncertainty estimates.

DGPFM effectively handles noisy, sparse, and irregular data.

Abstract

Learning mappings between functional spaces, also known as function-on-function regression, is a fundamental problem in functional data analysis with broad applications, including spatiotemporal forecasting, curve prediction, and climate modeling. Existing approaches often struggle to capture complex nonlinear relationships and/or provide reliable uncertainty quantification when data are noisy, sparse, or irregularly sampled. To address these challenges, we propose Deep Gaussian Processes for Functional Maps (DGPFM). Our method constructs a sequence of GP-based linear and nonlinear transformations directly in function space, leveraging kernel integral transforms, GP conditional means, and nonlinear activations sampled from Gaussian processes. A key insight enables a simplified and flexible implementation: under fixed evaluation locations, discrete approximations of kernel integral transforms reduce to direct functional integral transforms, allowing seamless integration of diverse transform designs. To support scalable probabilistic inference, we adopt inducing points and whitening transformations within a variational learning framework. Empirical results on both real-world and synthetic benchmark datasets demonstrate the advantages of DGPFM in terms of predictive accuracy and uncertainty calibration.