51. A Polarized Random Fourier Feature Kernel Least-Mean-Square Algorithm
- Author
-
Xu Yonghui, Jingli Yang, Yuqi Liu, and Shouda Jiang
- Subjects
General Computer Science ,Computer science ,polarized random Fourier features ,02 engineering and technology ,Nonlinear adaptive filtering ,01 natural sciences ,kernel polarization method ,symbols.namesake ,Kernel least mean square ,0202 electrical engineering, electronic engineering, information engineering ,Kernel adaptive filtering ,General Materials Science ,0101 mathematics ,Time series ,Training set ,General Engineering ,020206 networking & telecommunications ,Kernel approximation ,Polarization (waves) ,010101 applied mathematics ,Fourier transform ,random Fourier features ,symbols ,lcsh:Electrical engineering. Electronics. Nuclear engineering ,Algorithm ,lcsh:TK1-9971 - Abstract
This paper presents a polarized random Fourier feature kernel least-mean-square algorithm that aims to overcome the dimension curve of the random Fourier feature kernel least-mean-square (RFFKLMS) algorithm. RFFKLMS is an effective nonlinear adaptive filtering algorithm based on the kernel approximation technique. However, random samples drawn from the distribution need more dimensions to achieve better-generalized performance because they are independent of the training data. To overcome this weakness, a kernel polarization method is adopted to optimize the random samples. Polarized random Fourier features demonstrate a clear advantage over a method without using the polarization method. The experimental results in the context of Lorenz time series prediction and channel equalization verify the effectiveness of the proposed method.
- Published
- 2019