We prove strong noise-tolerance properties of a potential-based boosting algorithm, similar to MadaBoost (Domingo and Watanabe, 2000) and SmoothBoost (Servedio, 2003). Our analysi...
We describe a novel family of PAC model algorithms for learning linear threshold functions. The new algorithms work by boosting a simple weak learner and exhibit complexity bounds...
We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalizatio...
Output coding is a general framework for solving multiclass categorization problems. Previous research on output codes has focused on building multiclass machines given predefine...
In the present paper, we present the theoretical basis, as well as an empirical validation, of a protocol designed to obtain effective VC dimension estimations in the case of a si...