Optimizing resources in model selection for support vector machine

doi:10.1016/j.patcog.2006.06.012

2007-03-01

PRE

Mohamed Cheriet

DOI：10.1016/j.patcog.2006.06.012

原文链接

原文求助

摘要

En 中文

Tuning support vector machine (SVM) hyperparameters is an important step in achieving a high-performance learning machine. It is usually done by minimizing an estimate of generalization error based on the bounds of the leave-one-out (LOO) such as radius-margin bound and on the performance measures such as generalized approximate cross-validation (GACV), empirical error, etc. These usual automatic methods used to tune the hyperparameters require an inversion of the Gram-Schmidt matrix or a resolution of an extra-quadratic programming problem. In the case of a large data set these methods require the addition of huge amounts of memory and a long CPU time to the already significant resources used in SVM training. In this paper, we propose a fast method based on an approximation of the gradient of the empirical error, along with incremental learning, which reduces the resources required both in terms of processing time and of storage space. We tested our method on several benchmarks, which produced promising results confirming our approach. Furthermore, it is worth noting that the gain time increases when the data set is large. (c) 2006 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

Keyword:

model selection

SVM

kernel

hyperparameters

optimizing time

AI总结

对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Pattern Recognition

IF:

7.6

论文数:

1.3W

被引数:

4.5W

机构

暂无机构信息

引用论文

Nonlinear Hybrid Planning with Deep Net Learned Transition Models and Mixed-Integer Linear Programming

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence

IF0

2017-08-01

OAAI

Buser Say; Ga Wu; Yu Qing Zhou; Scott Sanner

Browplasty as an adjunct to rhinoplasty

Head & Neck Surgery

IF0

2006-07-18

PREAI

Richard C. Webster; Terence M. Davidson; Richard C. Smith

Monitoring of the Training Load and Well-Being of Elite Rhythmic Gymnastics Athletes in 25 Weeks: A Comparison between Starters and Reserves

Sports

IF0

2022-11-28

OAAI

Iohanna Fernandes; João H. Gomes; Levy de Oliveira; Marcos Almeida; João G. Claudino; Camila Resende; Dermival R. Neto; Mónica Hontoria Galán; Paulo Márcio P. Oliveira; Felipe J. Aidar; Renata Mendes; Marzo E. Da Silva-Grigoletto

Choosing multiple parameters for support vector machines

MACHINE LEARNING

IF2.9

2002-01-01

2.0K