Gaussian Processes for Nonlinear Signal Processing

Abstract

Gaussian processes (GPs) are versatile tools that have been successfully employed to solve nonlinear estimation problems in machine learning, but that are rarely used in signal processing. In this tutorial, we present GPs for regression as a natural nonlinear extension to optimal Wiener filtering. After establishing their basic formulation, we discuss several important aspects and extensions, including recursive and adaptive algorithms for dealing with non-stationarity, low-complexity solutions, non-Gaussian noise models and classification scenarios. Furthermore, we provide a selection of relevant applications to wireless digital communications.

Cited by in corpus (10)

• A Gaussian process latent force model for joint input-state estimation in linear structural systems
• Online learning-based Model Predictive Control with Gaussian Process Models and Stability Guarantees
• Kernel Methods for Accurate UWB-Based Ranging with Reduced Complexity
• Complex-Valued Gaussian Processes for Regression
• Ultra-Reliable and Low-Latency Vehicular Communication: An Active Learning Approach
• Recursive Estimation of Dynamic RSS Fields Based on Crowdsourcing and Gaussian Processes
• Gaussian process classification using posterior linearisation
• Ensemble Kalman Filtering for Online Gaussian Process Regression and Learning
• An Exploratory Method for Smooth/Transient Decomposition
• An Efficient QAM Detector via Nonlinear Post-distortion based on FDE Bank under PA Impairments