| | |
Summary: Proceedings of the 18th Annual Conference on Learning Theory, 2005
Stability and Generalization of Bipartite Ranking
Algorithms
Shivani Agarwal1
and Partha Niyogi2
1
Department of Computer Science, University of Illinois at Urbana-Champaign
201 N. Goodwin Avenue, Urbana, IL 61801, USA
sagarwal@cs.uiuc.edu
2
Departments of Computer Science and Statistics, University of Chicago
1100 E. 58th Street, Chicago, IL 60637, USA
niyogi@cs.uchicago.edu
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
|
