Stability of transductive regression algorithms

Authors:
Corinna Cortes;Mehryar Mohri;Dmitry Pechyony;Ashish Rastogi
Affiliations:
Google Research, New York, NY;Courant Institute of Mathematical Sciences and Google Research, New York, NY;Israel Institute of Technology, Haifa, Israel;Courant Institute of Mathematical Sciences, New York, NY
Venue:
Proceedings of the 25th international conference on Machine learning
Year:
2008

Citing 4
Cited 2

Metric-Based Methods for Adaptive Model Selection and Regularization

Machine Learning
Stability and generalization

The Journal of Machine Learning Research
Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics)

Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics)
Stable transductive learning

COLT'06 Proceedings of the 19th annual conference on Learning Theory

Sampling methods for the Nyström method

The Journal of Machine Learning Research
Active search on graphs

Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining

Quantified Score

Hi-index	0.00

Visualization

Abstract

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 suggests that several existing algorithms might not be stable but prescribes a technique to make them stable. It also reports the results of experiments with local transductive regression demonstrating the benefit of our stability bounds for model selection, in particular for determining the radius of the local neighborhood used by the algorithm.