Saved in:
Bibliographic Details
Main Authors: Yang, Zewen, Zhang, Dongfa, Dai, Xiaobing, Yu, Fengyi, Zhang, Chi, Huang, Bingkun, Sadeghian, Hamid, Haddadin, Sami
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.03679
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911266250948608
author Yang, Zewen
Zhang, Dongfa
Dai, Xiaobing
Yu, Fengyi
Zhang, Chi
Huang, Bingkun
Sadeghian, Hamid
Haddadin, Sami
author_facet Yang, Zewen
Zhang, Dongfa
Dai, Xiaobing
Yu, Fengyi
Zhang, Chi
Huang, Bingkun
Sadeghian, Hamid
Haddadin, Sami
contents Gaussian Processes (GPs), as a nonparametric learning method, offer flexible modeling capabilities and calibrated uncertainty quantification for function approximations. Additionally, GPs support online learning by efficiently incorporating new data with polynomial-time computation, making them well-suited for safety-critical dynamical systems that require rapid adaptation. However, the inference and online updates of exact GPs, when processing streaming data, incur cubic computation time and quadratic storage memory complexity, limiting their scalability to large datasets in real-time settings. In this paper, we propose a streaming kernel-induced progressively generated expert framework of Gaussian processes (SkyGP) that addresses both computational and memory constraints by maintaining a bounded set of experts, while inheriting the learning performance guarantees from exact Gaussian processes. Furthermore, two SkyGP variants are introduced, each tailored to a specific objective, either maximizing prediction accuracy (SkyGP-Dense) or improving computational efficiency (SkyGP-Fast). The effectiveness of SkyGP is validated through extensive benchmarks and real-time control experiments demonstrating its superior performance compared to state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03679
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Streaming Generated Gaussian Process Experts for Online Learning and Control: Extended Version
Yang, Zewen
Zhang, Dongfa
Dai, Xiaobing
Yu, Fengyi
Zhang, Chi
Huang, Bingkun
Sadeghian, Hamid
Haddadin, Sami
Machine Learning
Systems and Control
Gaussian Processes (GPs), as a nonparametric learning method, offer flexible modeling capabilities and calibrated uncertainty quantification for function approximations. Additionally, GPs support online learning by efficiently incorporating new data with polynomial-time computation, making them well-suited for safety-critical dynamical systems that require rapid adaptation. However, the inference and online updates of exact GPs, when processing streaming data, incur cubic computation time and quadratic storage memory complexity, limiting their scalability to large datasets in real-time settings. In this paper, we propose a streaming kernel-induced progressively generated expert framework of Gaussian processes (SkyGP) that addresses both computational and memory constraints by maintaining a bounded set of experts, while inheriting the learning performance guarantees from exact Gaussian processes. Furthermore, two SkyGP variants are introduced, each tailored to a specific objective, either maximizing prediction accuracy (SkyGP-Dense) or improving computational efficiency (SkyGP-Fast). The effectiveness of SkyGP is validated through extensive benchmarks and real-time control experiments demonstrating its superior performance compared to state-of-the-art approaches.
title Streaming Generated Gaussian Process Experts for Online Learning and Control: Extended Version
topic Machine Learning
Systems and Control
url https://arxiv.org/abs/2508.03679