Dynamic Mixture of Experts Models for Online Prediction. Issue 2 (3rd April 2023)

• Record Type: Journal Article
• Authors: Munezero, Parfait; Villani, Mattias; Kohn, Robert
• Is Part Of: Technometrics. Volume 65:Issue 2(2023)
• Page Start: 257
• Page End: 268
• Publication Date: 2023-04-03
• Subjects: Bayesian sequential inference -- Linear Bayes -- Mixture models -- Particle filtering -- Sequential Monte Carlo; Statistical physics -- Periodicals; Chemistry -- Statistical methods -- Periodicals; Engineering -- Statistical methods -- Periodicals; 519.5
• DOI: 10.1080/00401706.2022.2146755
• Languages: English
• ISSNs: 0040-1706

Abstract

Abstract: A mixture of experts models the conditional density of a response variable using a mixture of regression models with covariate-dependent mixture weights. We extend the finite mixture of experts model by allowing the parameters in both the mixture components and the weights to evolve in time by following random walk processes. Inference for time-varying parameters in richly parameterized mixture of experts models is challenging. We propose a sequential Monte Carlo algorithm for online inference based on a tailored proposal distribution built on ideas from linear Bayes methods and the EM algorithm. The method gives a unified treatment for mixtures with time-varying parameters, including the special case of static parameters. We assess the properties of the method on simulated data and on industrial data where the aim is to predict software faults in a continuously upgraded large-scale software project.