Parallel Gaussian Process Regression with Low-Rank Covariance Matrix Approximations
arXiv:1305.5826
Abstract
Gaussian processes (GP) are Bayesian non-parametric models that are widely used for probabilistic regression. Unfortunately, it cannot scale well with large data nor perform real-time predictions due to its cubic time cost in the data size. This paper presents two parallel GP regression methods that exploit low-rank covariance matrix approximations for distributing the computational load among parallel machines to achieve time efficiency and scalability. We theoretically guarantee the predictive performances of our proposed parallel GPs to be equivalent to that of some centralized approximate GP regression methods: The computation of their centralized counterparts can be distributed among parallel machines, hence achieving greater time efficiency and scalability. We analytically compare the properties of our parallel GPs such as time, space, and communication complexity. Empirical evaluation on two real-world datasets in a cluster of 20 computing nodes shows that our parallel GPs are significantly more time-efficient and scalable than their centralized counterparts and exact/full GP while achieving predictive performances comparable to full GP.
29th Conference on Uncertainty in Artificial Intelligence (UAI 2013), Extended version with proofs, 13 pages
References in corpus (3)
- Multi-Robot Informative Path Planning for Active Sensing of Environmental Phenomena: A Tale of Two Algorithms
- Decentralized Data Fusion and Active Sensing with Mobile Sensors for Modeling and Predicting Spatiotemporal Traffic Phenomena
- Active Markov Information-Theoretic Path Planning for Robotic Environmental Sensing
Cited by in corpus (7)
- Parallel Gaussian Process Regression with Low-Rank Covariance Matrix Approximations
- Patchwork Kriging for Large-scale Gaussian Process Regression
- GP-Localize: Persistent Mobile Robot Localization using Online Sparse Gaussian Process Observation Model
- Sparse Additive Gaussian Process Regression
- Bayesian Analysis Reveals the Key to Extracting Pair Potentials from Neutron Scattering Data
- Gaussian Process Decentralized Data Fusion Meets Transfer Learning in Large-Scale Distributed Cooperative Perception
- Revisiting the Sample Complexity of Sparse Spectrum Approximation of Gaussian Processes