We address the problem of learning distance metrics using side-information in the form of groups of "similar" points. We propose to use the RCA algorithm, which is a sim...
Abstract. The problem of averaging outcomes under several scenarios to form overall objective functions is of considerable importance in decision support under uncertainty. The fuz...
The absolute loss is the absolute difference between the desired and predicted outcome. I demonstrateworst-case upper bounds on the absolute loss for the perceptron algorithm and ...
Several reinforcement-learning techniques have already been applied to the Acrobot control problem, using linear function approximators to estimate the value function. In this pape...
We introduce several generalizations of classical computer science problems obtained by replacing simpler objective functions with general submodular functions. The new problems i...