We present BL-WoLF, a framework for learnability in repeated zero-sum games where the cost of learning is measured by the losses the learning agent accrues (rather than the number...
Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, inc...
A set of jobs need to be served by a single server which can serve only one job at a time. Jobs have processing times and incur waiting costs (linear in their waiting time). The j...
Abstract Computer vision is full of problems elegantly expressed in terms of energy minimization. We characterize a class of energies with hierarchical costs and propose a novel hi...
Andrew Delong, Lena Gorelick, Olga Veksler, Yuri B...
Abstract We present a new margin-based approach to first-order rule learning. The approach addresses many of the prominent challenges in first-order rule learning, such as the comp...