Fetching the paper…

Reading the bibliography…

2012

GPU acceleration of the particle filter: the Metropolis resampler

Murray, Lawrence

Original
PDF
Post on X

Understand

We consider deployment of the particle filter on modern massively parallel hardware architectures, such as Graphics Processing Units (GPUs), with a focus on the resampling stage.

While standard multinomial and stratified resamplers require a sum of importance weights computed collectively between threads, a Metropolis resampler favourably requires only pair-wise ratios between weights, computed independently by threads, and can be further tuned for performance by adjusting its number of iterations.
While achieving respectable results for the stratified and multinomial resamplers, we demonstrate that a Metropolis resampler can be faster where the variance in importance weights is modest, and so is worth considering in a performance-critical context, such as particle Markov chain Monte Carlo and real-time applications.

GPU acceleration of the particle filter: the Metropolis resampler · Around

Built on

A model of annual plankton cycles
G. Evans and J. Parslow · 1985
Earlier work this paper cites.
How many iterations in the Gibbs sampler?
A. E. Raftery and S. Lewis · 1992
Earlier work this paper cites.
Novel approach to nonlinear/non-Gaussian Bayesian state estimation
N. Gordon, D. Salmond, and A. Smith · 1993
Earlier work this paper cites.
Monte Carlo filter and smoother for non-Gaussian nonlinear state space models
G. Kitagawa · 1996
Earlier work this paper cites.
Maximally equidistributed combined Tausworthe generators
P. L’Ecuyer · 1996
Earlier work this paper cites.

Similar

Sequential Monte Carlo Methods in Practice
A. Doucet, N. de Freitas, and N. Gordon, editors · 2001
Cited alongside, same era.
Resampling algorithms for particle filters: A computational complexity perspective
M. Bolić, P. M. Djurić, , and S. Hong · 2004
Cited alongside, same era.
Resampling algorithms and architectures for distributed particle filters
M. Bolić, P. M. Djurić, and S. Hong · 2005
Cited alongside, same era.
A graphics processing unit implementation of the particle filter
G. Hendeby, J. D. Hol, R. Karlsson, and F. Gustafsson · 2007
Cited alongside, same era.
A GPU-accelerated particle filter with pixel-level likelihood
C. Lenz, G. Panin, and A. Knoll · 2008
Cited alongside, same era.

Then

Efficient parallel scan algorithms for GPUs
S. Sengupta, M. Harris, and M. Garland · 2008
Later among the works it cites.
Particle Markov chain Monte Carlo methods
C. Andrieu, A. Doucet, and R. Holenstein · 2010
Later among the works it cites.
Thrust: A parallel template library, 2010
J. Hoberock and N. Bell · 2010
Later among the works it cites.
A Bayesian approach to state and parameter estimation in a phytoplankton-zooplankton model
E. Jones, J. Parslow, and L. M. Murray · 2010
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…