Generalization bounds for ranking algorithms via almost everywhere stability

Tianwei Xu Tianwei Xu,Jianhou Gan Jianhou Gan,Wei Gao Wei Gao,Yungang Zhang Yungang Zhang

doi:10.1109/iccrd.2011.5763955

Generalization bounds for ranking algorithms via almost everywhere stability

Tianwei Xu Tianwei Xu, Jianhou Gan Jianhou Gan + Show 2 more

https://doi.org/10.1109/iccrd.2011.5763955

Copy DOI

Publication Date: Mar 1, 2011

Citations: 5

Affiliation: Yunnan Normal University, Soochow University, University of Liverpool

#Notions Of Strong Stability #Ranking Algorithms + Show 8 more

Abstract
Full-Text PDF
Similar Papers

Abstract

The goal of ranking is to learn a real-valued ranking function that induces a ranking or ordering over an instance space. A learning algorithm is stable if the algorithm satisfies the hypothesis that the output of the algorithm varies in a limited way in response to small changes made to the training set. This paper studies the `almost everywhere' stability of ranking algorithms, notions of strong stability and weak stability for ranking algorithms are defined, and the generalization bounds of stable ranking algorithms are obtained. In particular, the relationship between strong (weak) loss stability and strong (weak) score stability is also discussed.

Full Text