.png){kind=icon}
.png){kind=icon}
Return
Fully Empirical and Data-Dependent Stability-Based Bounds
.png){kind=icon}
PRE
AI
DOI：10.1109/TCYB.2014.2361857.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
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.
Keywords:
Algorithmic stability
data-dependent bounds
fully empirical bounds
in-sample
model selection
out-of-sample
support vector machine (SVM)
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
10.5
Papers:
1.1W
Citations:
5.0W