Imperial College London
Portrait Picture

Professor Axel Gandy

Faculty of Natural Sciences, Department of Mathematics

Head of Department of Mathematics & Chair in Statistics
 
 
 
//

Contact

 

+44 (0)20 7594 8518a.gandy Website

 
 
//

Location

 

644Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Gandy:2016:10.1109/TSP.2016.2558166,
author = {Gandy, A and Lau, F},
doi = {10.1109/TSP.2016.2558166},
journal = {IEEE Transactions on Signal Processing},
pages = {4273--4281},
title = {The chopthin algorithm for resampling},
url = {http://dx.doi.org/10.1109/TSP.2016.2558166},
volume = {64},
year = {2016}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Resampling is a standard step in particle filters and more generally sequential Monte Carlo methods. We present an algorithm, called chopthin, for resampling weighted particles. In contrast to standard resampling methods the algorithm does not produce a set of equally weighted particles; instead it merely enforces an upper bound on the ratio between the weights. Simulation studies show that the chopthin algorithm consistently outperforms standard resampling methods. The algorithms chops up particles with large weight and thins out particles with low weight, hence its name. It implicitly guarantees a lower bound on the effective sample size. The algorithm can be implemented efficiently, making it practically useful. We show that the expected computational effort is linear in the number of particles. Implementations for C++, R (on CRAN), Python and Matlab are available.
AU  - Gandy,A
AU  - Lau,F
DO  - 10.1109/TSP.2016.2558166
EP  - 4281
PY  - 2016///
SN  - 1941-0476
SP  - 4273
TI  - The chopthin algorithm for resampling
T2  - IEEE Transactions on Signal Processing
UR  - http://dx.doi.org/10.1109/TSP.2016.2558166
UR  - http://hdl.handle.net/10044/1/30887
VL  - 64
ER  -
Download