Data augmentation for non-Gaussian regression models using variance-mean mixtures
From MaRDI portal
Abstract: We use the theory of normal variance-mean mixtures to derive a data-augmentation scheme for a class of common regularization problems. This generalizes existing theory on normal variance mixtures for priors in regression and classification. It also allows variants of the expectation-maximization algorithm to be brought to bear on a wider range of models than previously appreciated. We demonstrate the method on several examples, including sparse quantile regression and binary logistic regression. We also show that quasi-Newton acceleration can substantially improve the speed of the algorithm without compromising its robustness.
Recommendations
- Improving the convergence properties of the data augmentation algorithm with an application to Bayesian mixture modeling
- Data transforming augmentation for heteroscedastic models
- Optimal Data Augmentation Strategies for Additive Models
- Generalised data augmentation and posterior inferences
- DATA AUGMENTATION AND DYNAMIC LINEAR MODELS
- Data augmentation via Lévy processes
Cited in
(18)- Quantile Co-Movement in Financial Markets: A Panel Quantile Model With Unobserved Heterogeneity
- Global-local mixtures: a unifying framework
- Data augmentation via Lévy processes
- DATA AUGMENTATION AND DYNAMIC LINEAR MODELS
- Bayesian Inference for Logistic Models Using Pólya–Gamma Latent Variables
- Identification of sparse FIR systems using a general quantisation scheme
- Comment on article by Rubio and Steel
- Horseshoe Regularisation for Machine Learning in Complex and Deep Models1
- An ensemble EM algorithm for Bayesian variable selection
- Data augmentation for Bayesian deep learning
- SURE-tuned bridge regression
- Bayesian boundary trend filtering
- The reciprocal Bayesian Lasso
- Logistic-beta processes for dependent random probabilities with beta marginals
- A sparse empirical Bayes approach to high-dimensional Gaussian process-based varying coefficient models
- Simplex quantile regression without crossing
- Prediction-based regularization using data augmented regression
- Rejoinder: ``Inference in two-piece location-scale models with Jeffreys priors
This page was built for publication: Data augmentation for non-Gaussian regression models using variance-mean mixtures
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5411047)
