Stability Analysis and Learning Bounds for Transductive Regression Algorithms

Details Stability Analysis and Learning Bounds for Transductive Regression Algorithms Stability Analysis and Learning Bounds for Transductive Regression Algorithms

2009-04-05

arxiv.org/abs/0904.0814v1

Computer Science

Learning

26 pages

Scientific paper

This paper uses the notion of algorithmic stability to derive novel generalization bounds for several families of transductive regression algorithms, both by using convexity and closed-form solutions. Our analysis helps compare the stability of these algorithms. It also shows that a number of widely used transductive regression algorithms are in fact unstable. Finally, it reports the results of experiments with local transductive regression demonstrating the benefit of our stability bounds for model selection, for one of the algorithms, in particular for determining the radius of the local neighborhood used by the algorithm.

Affiliated with

Also associated with

No associations

Rating

Stability Analysis and Learning Bounds for Transductive Regression Algorithms 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 Stability Analysis and Learning Bounds for Transductive Regression Algorithms, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Stability Analysis and Learning Bounds for Transductive Regression Algorithms will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-132574