Inferring Latent Structure From Mixed Real and Categorical Relational Data
Repository Usage Stats
We consider analysis of relational data (a matrix), in which the rows correspond to subjects (e.g., people) and the columns correspond to attributes. The elements of the matrix may be a mix of real and categorical. Each subject and attribute is characterized by a latent binary feature vector, and an inferred matrix maps each row-column pair of binary feature vectors to an observed matrix element. The latent binary features of the rows are modeled via a multivariate Gaussian distribution with low-rank covariance matrix, and the Gaussian random variables are mapped to latent binary features via a probit link. The same type construction is applied jointly to the columns. The model infers latent, low-dimensional binary features associated with each row and each column, as well correlation structure between all rows and between all columns.
More InfoShow full item record
James L. Meriam Distinguished Professor of Electrical and Computer Engineering
Lawrence Carin earned the BS, MS, and PhD degrees in electrical engineering at the University of Maryland, College Park, in 1985, 1986, and 1989, respectively. In 1989 he joined the Electrical Engineering Department at Polytechnic University (Brooklyn) as an Assistant Professor, and became an Associate Professor there in 1994. In September 1995 he joined the Electrical and Computer Engineering (ECE) Department at Duke University, where he is now a Professor. He was ECE Department Chair from 2011
Associate Research Professor in the Department of Psychology and Neuroscience
NOTE: As of 8/1/2015 Dr. Mitroff and his lab will move to The George Washington University in Washington D.C. Lab focus: My lab has an active interest in visual search—how we find targets amongst distractors. With a dual goal of informing both academic theory and applied "real-world" performance, we explore various influences on search. We work with a variety of expert groups to understand the effects of experience and expertise, and to reveal individual differences in performa
Alphabetical list of authors with Scholars@Duke profiles.