We present an algorithm, called the offset tree, for learning in situations where a loss associated with different decisions is not known, but was randomly probed. The algorithm i...
Software upgrades are unreliable, often causing downtime or data loss. I propose Imago, an approach for removing the leading causes of upgrade failures (broken dependencies) and o...
A new outer bound on the capacity region of Gaussian interference channels is developed. The bound combines and improves existing genie-aided methods and is shown to give the sum-r...
The association of perception and action is key to learning by observation in general, and to programlevel task imitation in particular. The question is how to structure this info...
We modify existing models of bacteriophage growth on an exponentially growing bacterial population by including (1) density dependent phage attack rates and (2) loss to phage due ...