We present a new subgoal-based method for automatically creating useful skills in reinforcement learning. Our method identifies subgoals by partitioning local state transition gra...
Both document clustering and word clustering are well studied problems. Most existing algorithms cluster documents and words separately but not simultaneously. In this paper we pr...
—We introduce a new tool for approximation and testing algorithms called partitioning oracles. We develop methods for constructing them for any class of bounded-degree graphs wit...
Avinatan Hassidim, Jonathan A. Kelner, Huy N. Nguy...
Segmenting different individuals in a group meeting and their speech is an important first step for various tasks such as meeting transcription, automatic camera panning, multime...