Transductive Rademacher complexity and its applications
Ran El-Yaniv and Dmitry Pechyony
In: COLT 2007, 13-15 June 2007, San Diego, CA, USA.
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.
|EPrint Type:||Conference or Workshop Item (Paper)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Subjects:||Theory & Algorithms|
|Deposited By:||Dmitry Pechyony|
|Deposited On:||07 February 2008|