In the context of binary classification, we define disagreement as a measure of how often two independently-trained models differ in their classification of unlabeled data. We exp...
Abstract We observe that the switching activity at a circuit node, also called the transition density, can be extremely sensitive to the circuit internal delays. As a result, sligh...
We introduce a computationally feasible, "constructive" active learning method for binary classification. The learning algorithm is initially formulated for separable cl...
This paper investigates the maximal channel coding rate achievable at a given blocklength and error probability. For general classes of channels new achievability and converse bou...
Yury Polyanskiy, H. Vincent Poor, Sergio Verd&uacu...
Motivated by a recent surge of interest in convex optimization techniques, convexity/concavity properties of error rates of the maximum likelihood detector operating in the AWGN ch...