Bayesian Computation - Why/when Variational Bayes, not MCMC or SMC?
Bayesian computation - Why/when Variational Bayes, not MCMC or SMC?
Variational Bayes Tutorial:
https://vbayeslab.github.io/VBLabDocs/
Abstract
Bayesian inference has been increasingly used in statistics and related areas as a principled and convenient tool for reasoning with uncertainty. Bayesian computation is often a challenging task and modern applications of Bayesian inference, such as Bayesian deep learning, have called for more scalable Bayesian computation techniques. In this talk, I will give a quick introduction to Variational Bayes for scalable Bayesian inference. I then provide a general discussion on its pros and cons, recent advances and applications, and some potential research directions.
Bio
Associate Professor Minh-Ngoc is currently with the Discipline of Business Analytics, University of Sydney Business School. He obtained a BSc and a MSc both in Mathematics from the Vietnam National University at Hanoi, and a PhD in Statistics in 2012 from the National University of Singapore.
Minh-Ngoc’s main research interest is Bayesian computation and statistical Machine Learning with a special focus on Variational Bayes. He is also working on bringing state-of-the-art quantum computation techniques into data analysis. He is interested in promoting the use of modern Bayesian computation techniques in Cognitive Science, Consumer Behaviour and Financial Econometrics. Minh-Ngoc also has industry experience – before studying his PhD, he worked with one of the largest banks in Vietnam to help develop its credit scoring system. Minh-Ngoc’s research has been published in many top-tier statistical journals and conferences. His research has been well funded with more than $1 million including three ARC grants. He is also an enthusiastic educator.