Stability Analysis and Learning Bounds for Transductive Regression Algorithms

Simple item page
dc.creatorCortes, Corinna
dc.creatorMohri, Mehryar
dc.creatorPechyony, Dmitry
dc.creatorRastogi, Ashish
dc.date2009-04-05
dc.date.accessioned2026-07-07T13:00:45Z
dc.date.available2026-07-07T13:00:45Z
dc.descriptionThis 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.
dc.description26 pages
dc.identifierhttps://arxiv.org/abs/0904.0814
dc.identifierhttp://arxiv.org/abs/0904.0814
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/225938
dc.subjectMachine Learning
dc.titleStability Analysis and Learning Bounds for Transductive Regression Algorithms
dc.typetext

Files

Collections

arXiv