Loss Decomposition for Fast Learning in Large Output Spaces

Ian En-Hsu Yen, Satyen Kale, Felix X. Yu, Daniel Niels Holtmann-Rice, Sanjiv Kumar, Pradeep Ravikumar

Abstract: For problems with large output spaces, evaluation of the loss function and its gradient are expensive, typically taking linear time in the size of the output space. Recently, methods have been deve...