Nikos Karampatziakis of Cornell University's Department of Computer Science, candidate for the Sheldon-Ekland Olson postdoctoral fellowship, presents a talk titled "Large Scale Agnostic Active Learning."
Karampatziakis presents an active learning algorithm that is theoretically sound in an agnostic setting, empirically effective and as efficient as standard online learning algorithms.
Location:
McCombs School of Business (CBA), Events Room 3.304