.png){kind=icon}
返回
Fully Empirical and Data-Dependent Stability-Based Bounds
.png){kind=icon}
PRE
AI
DOI：10.1109/TCYB.2014.2361857.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The purpose of this paper is to obtain a fully empirical stability-based bound on the generalization ability of a learning procedure, thus, circumventing some limitations of the structural risk minimization framework. We show that assuming a desirable property of a learning algorithm is sufficient to make data-dependency explicit for stability, which, instead, is usually bounded only in an algorithmic-dependent way. In addition, we prove that a well-known and widespread classifier, like the support vector machine (SVM), satisfies this condition. The obtained bound is then exploited for model selection purposes in SVM classification and tested on a series of real-world benchmarking datasets demonstrating, in practice, the effectiveness of our approach.
Keyword:
Algorithmic stability
data-dependent bounds
fully empirical bounds
in-sample
model selection
out-of-sample
support vector machine (SVM)
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
IF:
10.5
论文数:
1.1W
被引数:
5.0W
机构
引用论文
.png){kind=icon}
分享收藏
查看更多内容