.png){kind=icon}
Return
On Optimal Learning With Random Features
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2022.3152270.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We consider supervised learning in a reproducing kernel Hilbert space (RKHS) using random features. We show that the optimal rate is obtained under suitable regularity conditions, and at the same time improving on the existing bounds on the number of random features required. As a straightforward extension, distributed learning in the simple setting of one-shot communication is also considered that achieves the same optimal rate.
Keywords:
Kernel
Standards
Urban areas
Time complexity
Supervised learning
Hilbert space
Convergence
Distributed learning
kernel method
optimal rate
random features
Journal
IF:
8.9
Papers:
7.6K
Citations:
7.2W
Organization
Cited Papers
ShareSaveRANDOMIZED SKETCHES FOR KERNELS: FAST AND OPTIMAL NONPARAMETRIC REGRESSION.png)
ANNALS OF STATISTICS
OAAI
ANNALS OF STATISTICSIF3.7
OAAIShareSaveShareSaveShareSave no more
no more