An adaptive truncation method for inference in Bayesian nonparametric models

Abstract

Many exact Markov chain Monte Carlo algorithms have been developed for posterior inference in Bayesian nonparametric models which involve infinitedimensional priors. However, these methods are not generic and special methodology must be developed for different classes of prior or different models. Alternatively, the infinite-dimensional prior can be truncated and standard Markov chain Monte Carlo methods used for inference. However, the error in approximating the infinite-dimensional posterior can be hard to control for many models. This paper describes an adaptive truncation method which allows the level of the truncation to be decided by the algorithm and so can avoid large errors in approximating the posterior. A sequence of truncated priors is constructed which are sampled using Markov chain Monte Carlo methods embedded in a sequential Monte Carlo algorithm. Implementational details for infinite mixture models with stick-breaking priors and normalized random measures with independent increments priors are discussed. The methodology is illustrated on infinite mixture models, a semiparametric linear mixed model and a nonparametric time series model.

Evaluating Traffic Congestion Using the Traffic Occupancy and Speed Distribution Relationship: An Application of Bayesian Dirichlet Process Mixtures of Generalized Linear Model

“…After the first break, the next break, 2 k = , has the probability ( ) On the other hand, when the process of breaking continues until the infinite number of clusters is created the model become nonparametric with infinite mixture states/components [21]. However, the literature point out that working with the infinite dimensional posterior distribution is computationally expensive [22].…”

Bayesian Nonparametric Vector Autoregressive Models

“…Journal of Econometrics (2018) Griffin (2016) which adaptively truncates the infinite sum in the numerator and denominator and tends to avoid large truncation errors in the posterior. We define a truncation of the infinite model in Eq.…”

“…The adaptive truncation method of Griffin (2016) uses an MCMC algorithm to sample from the posterior, π K 0 (θ 1:K 0 , η 1:K 0 |y), for a user-defined starting value, K 0 , and then uses a sequential Monte Carlo method to sample from the sequence of posterior distributions…”

A blocked Gibbs sampler for NGG-mixture models via a priori truncation

“…Recently, an a priori truncation method has been introduced by Griffin (2013), who proposes an adaptive truncation algorithm for posterior inference with priors either of stick-breaking or NRMI type.…”

“…On the other hand, as pointed out in Griffin (2013), there are two motivations for truncation: the study of the properties of the prior distribution, which is not our primary goal, and simpler calculation of posterior inference using these priors. Instead, with regard to theoretical results on approximation of Dirichlet processes based on the distributional equation for a DP given in Sethuraman (1994), we refer here to Muliere and Tardella (1998) and Favaro et al (2012).…”