Subsampling Sequential Monte Carlo for Static Bayesian Models

05/08/2018
by   David Gunawan, et al.
0

Our article shows how to carry out Bayesian inference by combining data subsampling with Sequential Monte Carlo (SMC). This takes advantage of the attractive properties of SMC for Bayesian computations with the ability of subsampling to tackle big data problems. SMC sequentially updates a cloud of particles through a sequence of densities, beginning with a density that is easy to sample from such as the prior and ending with the posterior density. Each update of the particle cloud consists of three steps: reweighting, resampling, and moving. In the move step, each particle is moved using a Markov kernel and this is typically the most computationally expensive part, particularly when the dataset is large. It is crucial to have an efficient move step to ensure particle diversity. Our article makes two important contributions. First, in order to speed up the SMC computation, we use an approximately unbiased and efficient annealed likelihood estimator based on data subsampling. The subsampling approach is more memory efficient than the corresponding full data SMC, which is a great advantage for parallel computation. Second, we use a Metropolis within Gibbs kernel with two conditional updates. First, a Hamiltonian Monte Carlo update makes distant moves for the model parameters. Second, a block pseudo-marginal proposal is used for the particles corresponding to the auxiliary variables for the data subsampling. We demonstrate the usefulness of the methodology using two large datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/26/2017

Particle rolling MCMC with double block sampling: conditional SMC update approach

An efficient simulation-based methodology is proposed for the rolling wi...
research
05/27/2022

Deterministic Langevin Monte Carlo with Normalizing Flows for Bayesian Inference

We propose a general purpose Bayesian inference algorithm for expensive ...
research
07/10/2014

Asynchronous Anytime Sequential Monte Carlo

We introduce a new sequential Monte Carlo algorithm we call the particle...
research
03/27/2023

Parameter estimation for many-particle models from aggregate observations: A Wasserstein distance based sequential Monte Carlo sampler

In this work we study systems consisting of a group of moving particles....
research
09/02/2021

Bayesian Detectability of Induced Polarisation in Airborne Electromagnetic Data using Reversible Jump Sequential Monte Carlo

Detection of induced polarisation (IP) effects in airborne electromagnet...
research
12/17/2017

Distributed SMC-PHD Fusion for Partial, Arithmetic Average Consensus

We propose an average consensus approach for distributed SMC-PHD (sequen...
research
09/04/2017

Unbiased approximations of products of expectations

We consider the problem of approximating the product of n expectations w...

Please sign up or login with your details

Forgot password? Click here to reset