Variational inference for count response semiparametric regression

By Jan Luts, Matt P. Wand. 2013

40 citations recorded by the source corpus.

Fast variational approximate algorithms are developed for Bayesian semiparametric regression when the response variable is a count, i.e. a non-negative integer. We treat both the Poisson and Negative Binomial families as models for the response variable. Our approach utilizes recently developed methodology known as non-conjugate variational message passing. For concreteness, we focus on generalized additive mixed models, although our variational approximation approach extends to a wide class of semiparametric regression models such as those containing interactions and elaborate random effect structure.

Subfields: Artificial Intelligence, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. David M. Blei
2. Alp Kucukelbir
3. Jon D. McAuliffe
4. David Rohde
5. Matt P. Wand
6. Stephan Mandt
7. Rajesh Ranganath
8. Michael I. Jordan

In Statistics and Probability

1. David Rohde
2. Alp Kucukelbir
3. Jon D. McAuliffe
4. David M. Blei
5. Matt P. Wand
6. David J. Nott
7. Rajesh Ranganath
8. Linda S. L. Tan

Citations in the corpus

• Variational Inference: A Review for Statisticians (2016, methodology): “, 2014), semiparametric regression models (Luts et al., 2015; Menictas and Wand, 2015), and nonparametric regression models (Pham et al.”
• Semiparametric Mean Field Variational Bayes: General Principles and Numerical Issues (2016, methodology): “In Luts and Wand (2015) and Menictas and Wand (2015), semiparametric mean field variational Bayes with Multivariate Normal pre-specification is applied, respectively, to count response semiparametric regression and heteroscedastic semiparametric regression.”