Consensus-based Recursive Multi-Output Gaussian Process

TL;DR

This paper introduces CRMGP, a scalable, distributed multi-output Gaussian process framework that maintains correlations and uncertainty calibration, suitable for large-scale sensing tasks.

Contribution

It develops a novel consensus-based recursive inference method enabling distributed learning with bounded computation for multi-output Gaussian processes.

Findings

CRMGP achieves competitive predictive performance.

CRMGP provides reliable uncertainty calibration.

CRMGP supports parallel, distributed learning with bounded computation.

Abstract

Multi-output Gaussian Processes provide principled uncertainty-aware learning of vector-valued fields but are difficult to deploy in large-scale, distributed, and streaming settings due to their computational and centralized nature. This paper proposes a Consensus-based Recursive Multi-Output Gaussian Process (CRMGP) framework that combines recursive inference on shared basis vectors with neighbour-to-neighbour information-consensus updates. The resulting method supports parallel, fully distributed learning with bounded per-step computation while preserving inter-output correlations and calibrated uncertainty. Experiments on synthetic wind fields and real LiDAR data demonstrate that CRMGP achieves competitive predictive performance and reliable uncertainty calibration, offering a scalable alternative to centralized Gaussian process models for multi-agent sensing applications.