College of LAS Events

Back to Listing

If you need disability-related accommodations in order to participate in a program or event and cannot find an event contact listed, please contact MT Hudson at (217) 333-0885 or Early requests are strongly encouraged to allow sufficient time to meet your access needs.

Statistics Seminar - Yun Yang, Florida State - "Fast and Optimal Bayesian Inference via Variational Approximations"

Event Type
106B1 - Engineering Hall
Nov 9, 2017   3:30 pm  
Originating Calendar
Department of Statistics Event Calendar

Title: Fast and Optimal Bayesian Inference via Variational Approximations



We propose a variational approximation to Bayesian posterior distributions, called $\alpha$-VB, with provable statistical guarantees for models with and without latent variables. The standard variational approximation is a special case of $\alpha$-VB with $\alpha=1$. When $\alpha \in(0,1)$, a novel class of variational inequalities are developed for linking the Bayes risk under the variational approximation to the objective function in the variational optimization problem, implying that maximizing the evidence lower bound in variational inference has the effect of minimizing the Bayes risk within the variational density family. Operating in a frequentist setup, the variational inequalities imply that point estimates constructed from the $\alpha$-VB procedure converge at an optimal rate to the true parameter in a wide range of problems. We illustrate our general theory with a number of examples, including the mean-field variational approximation to (low)-high-dimensional Bayesian linear regression with spike and slab priors, mixture of Gaussian models, latent Dirichlet allocation, and (mixture of) Gaussian variational approximation in regular parametric models.

link for robots only