# Federated Gaussian Process Learning via Pseudo-Representations for Large-Scale Multi-Robot Systems

Source: [Federated Gaussian Process Learning via Pseudo-Representations for Large-Scale Multi-Robot Systems](<https://www.sota2.com/research/paper/698eb05bc97a0b3e3b5e6981>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-14T05:00:14.824Z

Authors: Sanket A. Salunkhe, George P. Kontoudis

Published: 2026-02-12T18:28:27.000Z

## Abstract

Multi-robot systems require scalable and federated methods to model complex environments under computational and communication constraints. Gaussian Processes (GPs) offer robust probabilistic modeling, but suffer from cubic computational complexity, limiting their applicability in large-scale deployments. To address this challenge, we introduce the pxpGP, a novel distributed GP framework tailored for both centralized and decentralized large-scale multi-robot networks. Our approach leverages sparse variational inference to generate a local compact pseudo-representation. We introduce a sparse variational optimization scheme that bounds local pseudo-datasets and formulate a global scaled proximal-inexact consensus alternating direction method of multipliers (ADMM) with adaptive parameter updates and warm-start initialization. Experiments on synthetic and real-world datasets demonstrate that pxpGP and its decentralized variant, dec-pxpGP, outperform existing distributed GP methods in hyperparameter estimation and prediction accuracy, particularly in large-scale networks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Spatial Prediction on SRTM N39W106 (test)](<https://www.sota2.com/research/sota/spatial-prediction-on-srtm-n39w106-test.md>): Spatial Prediction; SRTM N39W106 (test); NRMSE: 0.058.

- [Spatial Prediction on SRTM N43W080 (test)](<https://www.sota2.com/research/sota/spatial-prediction-on-srtm-n43w080-test.md>): Spatial Prediction; SRTM N43W080 (test); NRMSE: 0.054.

- [Spatial Prediction on SRTM N37W120 (test)](<https://www.sota2.com/research/sota/spatial-prediction-on-srtm-n37w120-test.md>): Spatial Prediction; SRTM N37W120 (test); NRMSE: 0.062.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.12243>)

[PDF](<https://arxiv.org/pdf/2602.12243.pdf>)