A0513
Title: Streamlined variational inference for sparse linear mixed model selection
Authors: Emanuele Degani - University of Padua (Italy)
Dorota Toczydlowska - UCL (United Kingdom)
Matt P Wand - University of Technology Sydney (Australia)
Luca Maestrini - The Australian National University (Australia) [presenting]
Abstract: Variational approximations facilitate fast approximate Bayesian inference for the parameters of a variety of statistical models, including linear mixed models. However, for models with a high number of fixed or random effects, simple application of standard variational inference principles does not lead to fast approximate inference algorithms, due to the size of model design matrices and inefficient treatment of sparse matrix problems arising from the required approximating density parameters updates. We illustrate how recently developed streamlined variational inference procedures can be generalized to make fast and accurate inference for the parameters of linear mixed models with nested random effects and global-local priors for Bayesian fixed effects selection. Our variational inference algorithms achieve convergence to the same optima of their standard implementations, although with significantly lower computational effort, memory usage and time, especially for large numbers of random effects.
