Some of the material in is restricted to members of the community. By logging in, you may be able to gain additional access to certain collections or items. If you have questions about access or logging in, please use the form on the Contact Page.
Count data are ubiquitous in modern statistical applications. How to modeling such data remains a challenging task in machine learning. In this study, we consider various aspects of statistical modeling on Poisson count data. Concerned with computational burdens for maximum likelihood estimation of the mean, we revisit the classical iterative proportional scaling and propose a set of methods that achieve computational scalability in high dimensional applications with regularized extensions for feature selection. In order to capture association effects given multivariate count data, we utilize the tool of non-Gaussian graph learning. We perform comprehensive empirical studies on synthetic data and real world data to demonstrate its power. Based on the concept of data depth, we investigate a non-parametric approach for modeling multivariate data. We utilize modern optimization techniques to provide scalable algorithms in high dimensional depth and depth median computations. Real-world examples are given to show the effectiveness of the proposed methods.