The chopthin algorithm for resampling

TL;DR

The paper introduces the chopthin resampling algorithm for particle filters, which maintains weight ratios within bounds, improves performance over standard methods, and is computationally efficient with multiple language implementations.

Contribution

The paper presents a novel resampling algorithm called chopthin that enforces weight ratio bounds, outperforming standard methods and ensuring efficiency.

Findings

Chopthin outperforms standard resampling methods in simulations.

It guarantees a lower bound on effective sample size.

The algorithm has linear expected computational effort.

Abstract

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.