Fast Variational Bayes Methods for Multinomial Probit Models
From MaRDI portal
Abstract: The multinomial probit model is often used to analyze choice behaviour. However, estimation with existing Markov chain Monte Carlo (MCMC) methods is computationally costly, which limits its applicability to large choice data sets. This paper proposes a variational Bayes method that is accurate and fast, even when a large number of choice alternatives and observations are considered. Variational methods usually require an analytical expression for the unnormalized posterior density and an adequate choice of variational family. Both are challenging to specify in a multinomial probit, which has a posterior that requires identifying restrictions and is augmented with a large set of latent utilities. We employ a spherical transformation on the covariance matrix of the latent utilities to construct an unnormalized augmented posterior that identifies the parameters, and use the conditional posterior of the latent utilities as part of the variational family. The proposed method is faster than MCMC, and can be made scalable to both a large number of choice alternatives and a large number of observations. The accuracy and scalability of our method is illustrated in numerical experiments and real purchase data with one million observations.
Cites work
- scientific article; zbMATH DE number 7625183 (Why is no real title available?)
- A Bayesian analysis of the multinomial probit model using marginal data augmentation
- A Symmetric prior for multinomial probit models
- Assessment and Adjustment of Approximate Inference Algorithms Using the Law of Total Variance
- Bayesian Analysis of Binary and Polychotomous Response Data
- Bayesian analysis of multivariate nominal measures using multivariate multinomial probit models
- Beyond Prediction: A Framework for Inference With Variational Approximations in Mixture Models
- Explaining variational approximations
- Fast and accurate variational inference for models with many latent variables
- Gaussian Variational Approximation With a Factor Covariance Structure
- Variational Bayesian Multinomial Probit Regression with Gaussian Process Priors
Cited in
(4)- Hybrid unadjusted Langevin methods for high-dimensional latent variable models
- Bayesian inference for multivariate probit model with latent envelope
- Scalable variational inference for multinomial probit models under large choice sets and sample sizes
- Large Skew-t Copula Models and Asymmetric Dependence in Intraday Equity Returns
This page was built for publication: Fast Variational Bayes Methods for Multinomial Probit Models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6190745)
