Strong and Weak Stability of Randomized Learning Algorithms

摘要：

　　An algorithm is called stable at a training set S if any change of a single point in S yields only a small change in the output.Stability of the learning algorithm is necessary for learnability in the supervised classification and regression setting.In this paper,we give formal definitions of strong and weak stability for randomized algorithms and prove non-asymptotic bounds on the difference between the empirical and expected error.

关键词： strong stability weak stability randomized learning algorithms generalization error empirical error

作者: Ke Luo Zhiyang Jia Wei Gao

作者单位: Shaoyang University Library, Shaoyang University, Shaoyang, Hunan, China Tourism and Culture College, Yunnan University, Lijiang, Yunnan, China School of Information, Yunnan Normal University, Kunming, Yunnan, China

会议类型: 国际会议

会议名称: 2012 IEEE 14th International Conference on Communication Technology(2012年第十四届通信技术国际会议(ICCT 2012))

会议地点: 成都

会议语种:英文

页码: 942-946

在线出版日期: 2012-11-09（万方平台首次上网日期，不代表论文的发表时间）