We show that the class of strongly connected graphical models with treewidth at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Prev...
Window systems are the primary mediator of user input and output in modern computing systems. They are also a commonly used interprocess communication mechanism. As a result, they...
Jonathan S. Shapiro, John Vanderburgh, Eric Northu...
The "minimum margin" of an ensemble classifier on a given training set is, roughly speaking, the smallest vote it gives to any correct training label. Recent work has sh...
Testing of 3D stacked ICs (SICs) is becoming increasingly important in the semiconductor industry. In this paper, we address the problem of test architecture optimization for 3D s...
Learning function relations or understanding structures of data lying in manifolds embedded in huge dimensional Euclidean spaces is an important topic in learning theory. In this ...