We describe an algorithm for learning in the presence of multiple criteria. Our technique generalizes previous approaches in that it can learn optimal policies for all linear pref...
Most learning to rank research has assumed that the utility of different documents is independent, which results in learned ranking functions that return redundant results. The fe...
Aleksandrs Slivkins, Filip Radlinski, Sreenivas Go...
Aimsof traditional planners had beenlimited to finding a sequenceof operators rather than finding an optimal or neax-optimalfinal state. Consequent]y, the performanceimprovementsy...
This paper presents an active learning method that directly optimizes expected future error. This is in contrast to many other popular techniques that instead aim to reduce versio...
We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradie...