Updating Variational Bayes: Fast sequential posterior inference
This work addresses the need for efficient online Bayesian inference, particularly for applications like real-time vehicle behavior prediction, but it is incremental as it builds on existing variational Bayesian methods.
The paper tackles the problem of slow posterior inference in Bayesian methods by proposing Updating Variational Bayes (UVB), a recursive algorithm for fast sequential posterior updates in online settings, achieving computational speed improvements through importance sampling in UVB-IS.
Variational Bayesian (VB) methods produce posterior inference in a time frame considerably smaller than traditional Markov Chain Monte Carlo approaches. Although the VB posterior is an approximation, it has been shown to produce good parameter estimates and predicted values when a rich classes of approximating distributions are considered. In this paper we propose Updating VB (UVB), a recursive algorithm used to update a sequence of VB posterior approximations in an online setting, with the computation of each posterior update requiring only the data observed since the previous update. An extension to the proposed algorithm, named UVB-IS, allows the user to trade accuracy for a substantial increase in computational speed through the use of importance sampling. The two methods and their properties are detailed in two separate simulation studies. Two empirical illustrations of the proposed UVB methods are provided, including one where a Dirichlet Process Mixture model with a novel posterior dependence structure is repeatedly updated in the context of predicting the future behaviour of vehicles on a stretch of the US Highway 101.