We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of C...
While most theoretical work in machine learning has focused on the complexity of learning, recently there has been increasing interest in formally studying the complexity of teach...
Abstract. Spatial Data Mining (SDM) has great potential in supporting public policy and in underpinning society functioning. One task in SDM is the discovery of characterization an...
d Abstract) Eric Allender Christopher Wilson Department of Computer Science Department of Computer Rutgers University and Information Science New Brunswick, NJ 08903, USA Universit...
Rademacher and Gaussian complexities are successfully used in learning theory for measuring the capacity of the class of functions to be learned. One of the most important propert...