The Variational Bayes Approximation In Bayesian Filtering

Abstract

The Variational Bayes (VB) approach is used as a one-step approximation for Bayesian filtering. It requires the availability of moments of the free-form distributional optimizers. The latter may have intractable functional forms. In this contribution, we replace these by appropriate fixed-form distributions yielding the required moments. We address two scenarios of this Restricted VB (RVB) approximation. For the first scenario, an application in identification of HMMs is given. In the second, the fixed-form distribution is generated via Particle Filtering (PF). It is shown that a new approximation of Rao-Blackwellized particle filtering is obtained in this scenario of RVB. Its performance is assessed for a simple nonlinear model. THE VB APPROXIMATIONThe VB approximation is a deterministic free-form optimization technique. It was first used in off-line inference problems [1] and extended to on-line inference of time-invariant parameters in [2]. The use of VB in Bayesian filtering was first discussed in [3]. The key theory is now reviewed.Theorem 1 (Variational Bayes (VB)) Let f (θ|D) be the posterior distribution of multivariate parameter, θ = [θ 1 , θ 2 ] , andf (θ|D) be an approximate distribution restricted to the set of conditionally independent distributions(1)The minimum of the Kullback-Leibler divergencẽis reached forwhere θ /i denotes the complement of θ i in θ. We will refer tõ f (θ|D) (7) as the VB-approximation, andf (θ i |D) (3) as the VB-marginals.The above theorem provides a powerful tool for approximation of joint pdfs in separable form [3]:Here, g (θ 1 , D) and h (θ 2 , D) are finite-dimensional vectors of compatible dimension. Using (4) in (3),where h(·) = Ef (θ2|D) [h (·)] are the VB-moments for θ 2 , and similarly for θ 1 . An Iterative VB (IVB) [3] moment-swapping algorithm is implied. In many non-linear cases of g and/or h, the VB-marginals (3) are non-standard in form, and so the required VB-moments are difficult to evaluate. In this contribution, we aim to replace any such non-standard VB-marginal with a tractable alternative, as follows.Corollary 1 (of Theorem 1: Restricted VB) Letf (θ|D) be a conditionally-independent approximation of f (θ|D) of the kindfwhere f (θ 2 |D) is a fixed-form distribution. Then, the minimal KL divergence (2), under (6), is reached forf (θ 2 |D) needs to be chosen judiciously, such that its momentsrequired in (7)-are available. These moments are substituted just once, without the need for IVB cycles. Some standard distributional approximation methods may be interpreted as special cases of RVB; e.g. (i) certainty equivalence, where f ≡ δ(θ 2 −θ 2 ), in which case (7) becomes the conditional, f θ 1 |D,θ 2 ; and (ii) the Quasi-Bayes (QB) approximation, BAYESIAN FILTERINGConsider the following model structurewhere θ t is known as the state variable. By Bayesian Filtering (BF), we mean the recursive evaluation of the filtering distribution f (θ t |D t ) using Bayes' rule. D t = [d 1 , . . . , d t ] denotes the history of observations. The computational flowch...

Learning and forgetting using reinforced Bayesian change detection

“…However, it is the first time, to our knowledge, that this family of algorithms is applied to the study of RL in animals. We show that the two algorithms (RL and SF) share deep common features: for instance, the HAFVF and other similar algorithms ([57]) can be used with a naive prior θ 0 set to 0, in which case the update equations reduce somehow to a classical Q-learning algorithm ([1] and Appendix B). Another interesting bound between the two fields emerges when the measure of the environment volatility is built hierarchically: an interesting consequence of the forgetting algorithm we propose is that, when observations are not made, the agent erases progressively its memory of past events.…”

“…In this model (see Fig 2), named the Hierarchical Adaptive Forgetting Variational Filter [1], specific prior configurations will bend the learning process to categorize surprising events either as contingency changes, or as accidents. In contrast with other models [57], w and b are represented with a rich probability distribution where both the expected values and variances have an impact on the model’s behaviour. For a given prior belief on z , a confident prior over w , centered on high values of this parameter, will lead to a lack of flexibility that would not be observed with a less confident prior, even if they have the same expectation.…”

Bayesian sparse Fourier representation of off-grid targets with application to experimental radar data

“…The EM algorithm can converge to a local, and not global, maximum [26, chap.5]. The VB algorithm is also sub-optimal because it is based on an approximation of the posterior distribution, and is dependent on the initialization [33].…”

Updating Variational Bayes: Fast sequential posterior inference

“…However, each of these approaches results in only a single posterior distribution conditioned on data up to some pre-specified time period T n , and do not provide a mechanism for the approximation to be updated at a later time period T n+1 following the availability of additional observations. Smidl (2004) and Broderick et al (2013) each consider VB approximations for Bayesian updating, resulting in a progressive sequence of approximate posterior distributions that each condition on data up to any given time period T n . Their approaches update to the time T n+1 by substitution of the time T n posterior with MFVB approximations, which are feasibly obtained due to assuming the model and approximation each adhere to a suitably defined exponential family form.…”

“…In these special settings, MFVB is able to linearly combine the available optimally converged auxiliary parameters. While Smidl (2004) is concerned with state space models, Broderick et al (2013) considers application to a latent Dirichlet allocation problem, and shows it performs favourably compared to the approach of Hoffman et al (2010) in terms of log predictive score and computational time.…”