Department of Mathematics
 Search | Help | Login | pdf version | printable version

Math @ Duke



Publications [#325339] of David B. Dunson


Papers Published

  1. Johndrow, JE; Bhattacharya, A; Dunson, DB, TENSOR DECOMPOSITIONS AND SPARSE LOG-LINEAR MODELS., The Annals of Statistics, vol. 45 no. 1 (January, 2017), pp. 1-38 [doi]
    (last updated on 2019/05/23)

    Contingency table analysis routinely relies on log-linear models, with latent structure analysis providing a common alternative. Latent structure models lead to a reduced rank tensor factorization of the probability mass function for multivariate categorical data, while log-linear models achieve dimensionality reduction through sparsity. Little is known about the relationship between these notions of dimensionality reduction in the two paradigms. We derive several results relating the support of a log-linear model to nonnegative ranks of the associated probability tensor. Motivated by these findings, we propose a new collapsed Tucker class of tensor decompositions, which bridge existing PARAFAC and Tucker decompositions, providing a more flexible framework for parsimoniously characterizing multivariate categorical data. Taking a Bayesian approach to inference, we illustrate empirical advantages of the new decompositions.
ph: 919.660.2800
fax: 919.660.2821

Mathematics Department
Duke University, Box 90320
Durham, NC 27708-0320