pith. sign in

arxiv: 1306.0040 · v1 · pith:MZHXF7DEnew · submitted 2013-05-31 · 📊 stat.CO · math.ST· stat.ML· stat.TH

Expectation-maximization for logistic regression

classification 📊 stat.CO math.STstat.MLstat.TH
keywords algorithmapproachconnectionexpectation-maximizationlogisticmethodregressionvariational-bayes
0
0 comments X
read the original abstract

We present a family of expectation-maximization (EM) algorithms for binary and negative-binomial logistic regression, drawing a sharp connection with the variational-Bayes algorithm of Jaakkola and Jordan (2000). Indeed, our results allow a version of this variational-Bayes approach to be re-interpreted as a true EM algorithm. We study several interesting features of the algorithm, and of this previously unrecognized connection with variational Bayes. We also generalize the approach to sparsity-promoting priors, and to an online method whose convergence properties are easily established. This latter method compares favorably with stochastic-gradient descent in situations with marked collinearity.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.