We provide a framework to exploit dependencies among arms in multi-armed bandit problems, when the dependencies are in the form of a generative model on clusters of arms. We find ...
Bayesian learning, widely used in many applied data-modeling problems, is often accomplished with approximation schemes because it requires intractable computation of the posterio...
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
This paper investigates relative precision and optimality of analyses for concurrent probabilistic systems. Aiming at the problem at the heart of probabilistic model checking ? com...
We present the first spatially adaptive data structure that answers approximate nearest neighbor (ANN) queries to points that reside in a geometric space of any constant dimension...
Jonathan Derryberry, Don Sheehy, Maverick Woo, Dan...