Exact learning of half-spaces over finite subsets of IRn from membership queries is considered. We describe the minimum set of labelled examples separating the target concept from ...
We give the first representation-independent hardness results for PAC learning intersections of halfspaces, a central concept class in computational learning theory. Our hardness ...
We state and analyze the first active learning algorithm which works in the presence of arbitrary forms of noise. The algorithm, A2 (for Agnostic Active), relies only upon the ass...
Maria-Florina Balcan, Alina Beygelzimer, John Lang...