Transductive Rademacher complexity and its applications
Ran El-Yaniv and Dmitry Pechyony
In: COLT 2007, 13-15 June 2007, San Diego, CA, USA.

Abstract

We present data-dependent error bounds for transductive learning based on transductive Rademacher complexity. For specific algorithms we provide bounds on their Rademacher complexity based on their ``unlabeled-labeled'' decomposition. This decomposition technique applies to many current and practical graph-based algorithms. Finally, we present a new PAC-Bayesian bound for mixtures of transductive algorithms based on our Rademacher bounds.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.

[Edit]