This is a study of a technique for deriving the session type of a program written in a statically typed imperative language from its control flow. We impose on our unlabelled sess...
We present a trainable sequential-inference technique for processes with large state and observation spaces and relational structure. Our method assumes "reliable observation...
In this article, I will consider Markov Decision Processes with two criteria, each defined as the expected value of an infinite horizon cumulative return. The second criterion is e...
We present and analyze an agnostic active learning algorithm that works without keeping a version space. This is unlike all previous approaches where a restricted set of candidate...
Alina Beygelzimer, Daniel Hsu, John Langford, Tong...
Graphical models are usually learned without regard to the cost of doing inference with them. As a result, even if a good model is learned, it may perform poorly at prediction, be...