Modulating scalable Gaussian processes for expressive statistical learning

Haitao Liu

doi:10.1016/j.patcog.2021.108121

Return

Modulating scalable Gaussian processes for expressive statistical learning

2021-12-01

王晓放 (Xiaofang Wang) *

DOI：10.1016/j.patcog.2021.108121

Original

Save

View PDF

Abstract

En 中文

For a learning task, Gaussian process (GP) is interested in learning the statistical relationship between inputs and outputs, since it offers not only the prediction mean but also the associated variability. The vanilla GP however is hard to learn complicated distribution with the property of, e.g., heteroscedastic noise, multi-modality and non-stationarity, from massive data due to the Gaussian marginal and the cubic complexity. To this end, this article studies new scalable GP paradigms including the non-stationary heteroscedastic GP, the mixture of GPs and the latent GP, which introduce additional latent variables to modulate the outputs or inputs in order to learn richer, non-Gaussian statistical representation. Particularly, we resort to different variational inference strategies to arrive at analytical or tighter evidence lower bounds (ELBOs) of the marginal likelihood for efficient and effective model training. Extensive numerical experiments against state-of-the-art GP and neural network (NN) counterparts on various tasks verify the superiority of these scalable modulated GPs, especially the scalable latent GP, for learning diverse data distributions. (c) 2021 Elsevier Ltd. All rights reserved.

Keywords:

Gaussian process

Modulation

Scalability

Heteroscedastic noise

Multi-modality

Non-stationarity

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.