Adaptiveness and consistency of a class of online ensemble learning algorithms. (28th October 2020)

• Record Type: Journal Article
• Authors: Young, Carol; Yao, Ningshi; Zhang, Fumin
• Other Names: Wan Yan guestEditor.; Yang Tao guestEditor.; Yuan Ye guestEditor.; Lewis Frank L. guestEditor.
• Is Part Of: International journal of robust and nonlinear control. Volume 31:Number 6(2021)
• Page Start: 2018
• Page End: 2043
• Publication Date: 2020-10-28
• Subjects: adaptiveness and consistency analysis -- ensemble learning -- expert‐based learning algorithm; Automatic control -- Periodicals; Control theory -- Periodicals; Nonlinear systems -- Periodicals; 629.836
• DOI: 10.1002/rnc.5292
• Languages: English
• ISSNs: 1049-8923

Abstract

Summary: Expert based ensemble learning algorithms often serve as online learning algorithms for an unknown, possibly time‐varying, probability distribution. Their simplicity allows flexibility in design choices, leading to variations that balance adaptiveness and consistency. This article provides an analytical framework to quantify the adaptiveness and consistency of expert based ensemble learning algorithms. With properly selected states, the algorithms are modeled as a Markov chains. Then quantitative metrics of adaptiveness and consistency can be calculated through mathematical formulas, other than relying on numerical simulations. Results are derived for several popular ensemble learning algorithms. Success of the method has also been demonstrated in both simulation and experimental results.