. Specifically, we minimize the Burg divergence of a low-rank kernel to an input kernel, subject to pairwise distance constraints. Our approach has several advantages over existing methods. First, we present a natural information-theoretic formulation for the problem. Second, the algorithm utilizes the methods

We consider the problem of online prediction with a linear model. In contrast to existing work in online regression, which regularizes based on squared loss or KL-divergence, we regularize using divergences arising from the Burg entropy. We demonstrate regret bounds for our resulting online

Abstract In the present paper we shall discuss the information capacity of a Gaussian channel through Kullback-Leibler's [2] information measure of directed divergence and maximized entropy by the normal distribution due to Burg

explicitly, we propose rankbased distance metric learning. Our approach overcomes the drawback of existing algorithms by comparing the distances only among the relevant and irrelevant objects for a given query. To avoid over-fitting, a regularizer based on the Burg matrix divergence is also introduced. We

Abstract—In this paper, we first introduce a smooth parametric family of Bregman-Csiszár quantum entropies including the von Neumann and Burg quantum entropies. We then describe the dualistic nature of Voronoi diagrams for 1-qubit quantum states inside the 3D Bloch ball representation. We show

(ODR) is considered as one of the most promising candidates to measure the transverse beam size and angular divergence. A thin stainless steel mask has been installed at 45o with respect to the DR target and normally to the beam propa-gation to reduce the contribution of synchrotron radiation (SR

of Fregean sense that diverge in their interpretation of sense as descriptive or non-descriptive. I argue that a descriptive notion of sense forces one to postulate non-conceptual content, which I further argue is an untenable position. I ultimately provide an alternative account to what I ascertain to be a

West Nile virus (WNV) is becoming more widespread and markedly effecting public health. We sequenced the complete polyprotein gene of a divergent WNV strain newly detected in a pool of Uranotaenia unguiculata mosquitoes in Austria. Phylogenetic analyses suggest that the new strain constitutes a

First and foremost, I would like to thank my advisor, Prof. Jennifer E. Michaels. I am most appreciative of your guidance over the last four years, from the basics of elastic waves to both short- and long-term career advice. I have grown a tremendous amount, both profes-sionally and personally, and am deeply grateful for your mentorship, patience, and support. I would also like to thank my Ph.D. committee for their valuable insight and sugges-

@ Printed on acid-free paper which falls within the guidelines of the ANSI