The Generalization Performance of Learning Algorithms Derived simultaneously through Algorithmic Stability and Space Complexity

摘要：

A main issue in machine learning theoretical research is to analyze the generalization performance of learning algorithms. The previous results describing the generalization performance of learning algorithms are based on either com-plexity of hypothesis space or stability property of learning algorithms. In this paper we go far beyond these classical frameworks by establishing the first generalization bounds of learning algorithms in terms of uniform stability and the covering number of function space for regularized least squares regression and SVM regression. To have a better understanding the results obtained in this paper, we compare the obtained generalization bounds with previously known results.

作者: JieXu Bin Zou

作者单位: Faculty of Mathematics and Computer Science Hubei University, Wuhan, 430062, China

会议类型: 国际会议

会议名称: 2011 Seventh International Conference on Natural Computation(第七届自然计算国际会议 ICNC 2011)

会议地点: 上海

会议语种:英文

页码: 298-302

在线出版日期: 2011-07-26（万方平台首次上网日期，不代表论文的发表时间）