期刊
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
卷 31, 期 6, 页码 2018-2043出版社
WILEY
DOI: 10.1002/rnc.5292
关键词
adaptiveness and consistency analysis; ensemble learning; expert‐ based learning algorithm
资金
- Air Force Office of Scientific Research [FA9550-19-1-0283]
- National Oceanic and Atmospheric Administration [NA16NOS0120028]
- National Science Foundation [CNS-1828678, GCR-1934836, SAS-1849228]
- Office of Naval Research [N00014-19-1-2266, N00014-19-1-2556]
- U.S. Naval Research Laboratory [N00173-17-1-G001, N00173-19-P-1412]
This article introduces an analytical framework to quantify the adaptiveness and consistency of expert based ensemble learning algorithms. By modeling the algorithms as Markov chains with properly selected states, quantitative metrics can be calculated through mathematical formulas, instead of relying on numerical simulations. Results for popular ensemble learning algorithms have been derived and the success of the method has been demonstrated in simulation and experimental results.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据