Curse-of-dimensionality revisited: Collapse of the particle filter in very large scale systems

Simple item page
dc.creatorBengtsson, Thomas
dc.creatorBickel, Peter
dc.creatorLi, Bo
dc.date2008-05-20
dc.date.accessioned2026-07-07T12:19:04Z
dc.date.available2026-07-07T12:19:04Z
dc.descriptionIt has been widely realized that Monte Carlo methods (approximation via a sample ensemble) may fail in large scale systems. This work offers some theoretical insight into this phenomenon in the context of the particle filter. We demonstrate that the maximum of the weights associated with the sample ensemble converges to one as both the sample size and the system dimension tends to infinity. Specifically, under fairly weak assumptions, if the ensemble size grows sub-exponentially in the cube root of the system dimension, the convergence holds for a single update step in state-space models with independent and identically distributed kernels. Further, in an important special case, more refined arguments show (and our simulations suggest) that the convergence to unity occurs unless the ensemble grows super-exponentially in the system dimension. The weight singularity is also established in models with more general multivariate likelihoods, e.g. Gaussian and Cauchy. Although presented in the context of atmospheric data assimilation for numerical weather prediction, our results are generally valid for high-dimensional particle filters.
dc.descriptionPublished in at http://dx.doi.org/10.1214/193940307000000518 the IMS Collections (http://www.imstat.org/publications/imscollections.htm) by the Institute of Mathematical Statistics (http://www.imstat.org)
dc.identifierhttps://arxiv.org/abs/0805.3034
dc.identifierhttp://arxiv.org/abs/0805.3034
dc.identifierIMS Collections 2008, Vol. 2, 316-334
dc.identifierdoi:10.1214/193940307000000518
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/212627
dc.subjectStatistics Theory
dc.subjectComputation
dc.subjectMethodology
dc.subject93E11, 62L12, 86A22, 60G50, 86A32, 86A10 (Primary)
dc.titleCurse-of-dimensionality revisited: Collapse of the particle filter in very large scale systems
dc.typetext

Files

Collections

arXiv