Ranking and empirical minimization of U-statistics

Details Ranking and empirical minimization of U-statistics Ranking and empirical minimization of U-statistics

2006-03-05

arxiv.org/abs/math/0603123v1

Mathematics

Statistics Theory

32 pages

Scientific paper

The problem of ranking/ordering instances, instead of simply classifying them, has recently gained much attention in machine learning. In this paper we formulate the ranking problem in a rigorous statistical framework. The goal is to learn a ranking rule for deciding, among two instances, which one is "better," with minimum ranking risk. Since the natural estimates of the risk are of the form of a U-statistic, results of the theory of U-processes are required for investigating the consistency of empirical risk minimizers. We establish in particular a tail inequality for degenerate U-processes, and apply it for showing that fast rates of convergence may be achieved under specific noise assumptions, just like in classification. Convex risk minimization methods are also studied.

Affiliated with

Also associated with

No associations

Rating

Ranking and empirical minimization of U-statistics does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Ranking and empirical minimization of U-statistics, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Ranking and empirical minimization of U-statistics will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-291996