Wasserstein-Splitting Gaussian Process Regression for Heterogeneous Online Bayesian Inference

07/26/2021
by   Michael E. Kepler, et al.
0

Gaussian processes (GPs) are a well-known nonparametric Bayesian inference technique, but they suffer from scalability problems for large sample sizes, and their performance can degrade for non-stationary or spatially heterogeneous data. In this work, we seek to overcome these issues through (i) employing variational free energy approximations of GPs operating in tandem with online expectation propagation steps; and (ii) introducing a local splitting step which instantiates a new GP whenever the posterior distribution changes significantly as quantified by the Wasserstein metric over posterior distributions. Over time, then, this yields an ensemble of sparse GPs which may be updated incrementally, and adapts to locality, heterogeneity, and non-stationarity in training data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/26/2018

Scalable Gaussian Process Inference with Finite-data Mean and Variance Guarantees

Gaussian processes (GPs) offer a flexible class of priors for nonparamet...
research
09/17/2019

Compositional uncertainty in deep Gaussian processes

Gaussian processes (GPs) are nonparametric priors over functions, and fi...
research
12/27/2020

A Tutorial on Sparse Gaussian Processes and Variational Inference

Gaussian processes (GPs) provide a framework for Bayesian inference that...
research
10/16/2022

Streaming PAC-Bayes Gaussian process regression with a performance guarantee for online decision making

As a powerful Bayesian non-parameterized algorithm, the Gaussian process...
research
05/23/2016

A Unifying Framework for Gaussian Process Pseudo-Point Approximations using Power Expectation Propagation

Gaussian processes (GPs) are flexible distributions over functions that ...
research
06/23/2018

A breakpoint detection in the mean model with heterogeneous variance on fixed time-intervals

This work is motivated by an application for the homogeneization of GNSS...
research
04/23/2020

Consistent Online Gaussian Process Regression Without the Sample Complexity Bottleneck

Gaussian processes provide a framework for nonlinear nonparametric Bayes...

Please sign up or login with your details

Forgot password? Click here to reset