DocumentCode
3318581
Title
Some notes on the stability of learning
Author
Yufeng Deng ; Guo, Jun ; Luo, Shoushan
Author_Institution
Sch. of Inf. Eng., Beijing Univ. of Posts & Telecommun., China
fYear
2005
fDate
30 Oct.-1 Nov. 2005
Firstpage
756
Lastpage
759
Abstract
Learning theory based on ERM principle, especially promoted by VC theory provides some conditions on the hypothesis space to ensure generalization. However, several successful learning algorithms including regularization learning, SVM, bagging and boost are not strictly ERM. So, scientists are looking for new foundation of learning. Stability conditions are perhaps new foundation. We give an exponential bound for generalization performance based on concentration inequality with strong CV stability.
Keywords
generalisation (artificial intelligence); learning (artificial intelligence); CV stability; VC theory; empirical risk minimization principle; learning theory; Bagging; Learning systems; Machine learning; Mathematics; Risk management; Stability; Support vector machines; Topology; Virtual colonoscopy; Zinc; Concentration inequality; generalization bound; strong CV stability;
fLanguage
English
Publisher
ieee
Conference_Titel
Natural Language Processing and Knowledge Engineering, 2005. IEEE NLP-KE '05. Proceedings of 2005 IEEE International Conference on
Print_ISBN
0-7803-9361-9
Type
conf
DOI
10.1109/NLPKE.2005.1598837
Filename
1598837
Link To Document