On Optimal Learning With Random Features

doi:10.1109/TNNLS.2022.3152270

2023-11-01

PRE

Jiamin Liu

Heng Lian *

DOI：10.1109/TNNLS.2022.3152270

原文链接

原文求助

摘要

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.

Keyword:

Kernel

Standards

Urban areas

Time complexity

Supervised learning

Hilbert space

Convergence

Distributed learning

kernel method

optimal rate

random features

期刊

IEEE Transactions on Neural Networks and Learning Systems

IF:

8.9

论文数:

7.5K

被引数:

7.2W

机构

Renmin University of China

学者数:

8.1K

论文数: 7.7K

被引数: 1.1W

City University of Hong Kong

学者数:

2.3W

论文数: 3.0W

被引数: 6.1W

引用论文

Towards a wireless and fully-implantable ECoG system

2013 Transducers & Eurosensors XXVII: The 17th International Conference on Solid-State Sensors, Actuators and Microsystems (TRANSDUCERS & EUROSENSORS XXVII)

IF0

2013-06-01

PREAI

E. Tolstosheeva; J. Hoeffmann; J. Pistor; D. Rotermund; T. Schellenberg; D. Boll; T. Hertzberg; V. Gordillo-Gonzalez; S. Mandon; D. Peters-Drolshagen; M. Schneider; K. Pawelzik; A. Kreiter; S. Paul; W. Lang

Perioperative Artificial Enteral Nutrition in Malnourished Esophageal and Stomach Cancer Patients and Its Impact on Postoperative Complications

Indian Journal of Surgical Oncology

IF0

2019-05-11