Stability and generalization of bipartite ranking algorithms

DMCA

Stability and generalization of bipartite ranking algorithms (2005)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Shivani Agarwal , Partha Niyogi

Venue:	Proceedings of the Eighteenth Annual Conference on Computational Learning Theory (COLT
Citations:	24 - 2 self

BibTeX

@INPROCEEDINGS{Agarwal05stabilityand,
    author = {Shivani Agarwal and Partha Niyogi},
    title = {Stability and generalization of bipartite ranking algorithms},
    booktitle = {Proceedings of the Eighteenth Annual Conference on Computational Learning Theory (COLT},
    year = {2005},
    pages = {32--47},
    publisher = {Springer}
}

OpenURL

Abstract

Abstract. The problem of ranking, in which the goal is to learn a real-valued ranking function that induces a ranking or ordering over an instance space, has recently gained attention in machine learning. We study generalization properties of ranking algorithms, in a particular setting of the ranking problem known as the bipartite ranking problem, using the notion of algorithmic stability. In particular, we derive generalization bounds for bipartite ranking algorithms that have good stability properties. We show that kernel-based ranking algorithms that perform regularization in a reproducing kernel Hilbert space have such stability properties, and therefore our bounds can be applied to these algorithms; this is in contrast with previous generalization bounds for ranking, which are based on uniform convergence and in many cases cannot be applied to these algorithms. A comparison of the bounds we obtain with corresponding bounds for classification algorithms yields some interesting insights into the difference in generalization behaviour between ranking and classification. 1

Keyphrases

bipartite ranking algorithm generalization behaviour many case generalization property instance space interesting insight previous generalization bound particular setting kernel-based ranking algorithm real-valued ranking function algorithmic stability ranking problem stability property bipartite ranking problem reproducing kernel hilbert space corresponding bound uniform convergence good stability property machine learning generalization bound classification algorithm

DMCA