Regularized Particle Filter with Langevin Resampling Step
The solution of an inverse problem involves the estimation of variables and parameters values given by the state-space system. While a general (infinite-dimensional) optimal filter theory [1, 2] exists for nonlinear systems with Gaussian or non-Gaussian noise, applications rely on (finite-dimensiona...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference item |
| Published: |
AMER INST PHYSICS
2010
|
| _version_ | 1797093756642525184 |
|---|---|
| author | Duan, L Farmer, C Moroz, I |
| author2 | Simos, T |
| author_facet | Simos, T Duan, L Farmer, C Moroz, I |
| author_sort | Duan, L |
| collection | OXFORD |
| description | The solution of an inverse problem involves the estimation of variables and parameters values given by the state-space system. While a general (infinite-dimensional) optimal filter theory [1, 2] exists for nonlinear systems with Gaussian or non-Gaussian noise, applications rely on (finite-dimensional) suboptimal approximations to the optimal filter for practical implementations. The most widely-studied filters of this kind include the Regularized Particle Filter (RPF) [3, 4] and the Ensemble Square Root Filter (EnSRF) [5]. The latter is an ad-hoc approximation to the Bayes Filter, while the former is rigorously formulated, based upon the Glivenko-Cantelli theorem. By introducing a new global resampling step to the RPF, the EnSRF is proved to approximate the RPF in a special case. |
| first_indexed | 2024-03-07T04:04:50Z |
| format | Conference item |
| id | oxford-uuid:c5cb0fe9-88c0-461a-b2ce-b57696e26e4b |
| institution | University of Oxford |
| last_indexed | 2024-03-07T04:04:50Z |
| publishDate | 2010 |
| publisher | AMER INST PHYSICS |
| record_format | dspace |
| spelling | oxford-uuid:c5cb0fe9-88c0-461a-b2ce-b57696e26e4b2022-03-27T06:33:36ZRegularized Particle Filter with Langevin Resampling StepConference itemhttp://purl.org/coar/resource_type/c_5794uuid:c5cb0fe9-88c0-461a-b2ce-b57696e26e4bSymplectic Elements at OxfordAMER INST PHYSICS2010Duan, LFarmer, CMoroz, ISimos, TPsihoyios, GTsitouras, CThe solution of an inverse problem involves the estimation of variables and parameters values given by the state-space system. While a general (infinite-dimensional) optimal filter theory [1, 2] exists for nonlinear systems with Gaussian or non-Gaussian noise, applications rely on (finite-dimensional) suboptimal approximations to the optimal filter for practical implementations. The most widely-studied filters of this kind include the Regularized Particle Filter (RPF) [3, 4] and the Ensemble Square Root Filter (EnSRF) [5]. The latter is an ad-hoc approximation to the Bayes Filter, while the former is rigorously formulated, based upon the Glivenko-Cantelli theorem. By introducing a new global resampling step to the RPF, the EnSRF is proved to approximate the RPF in a special case. |
| spellingShingle | Duan, L Farmer, C Moroz, I Regularized Particle Filter with Langevin Resampling Step |
| title | Regularized Particle Filter with Langevin Resampling Step |
| title_full | Regularized Particle Filter with Langevin Resampling Step |
| title_fullStr | Regularized Particle Filter with Langevin Resampling Step |
| title_full_unstemmed | Regularized Particle Filter with Langevin Resampling Step |
| title_short | Regularized Particle Filter with Langevin Resampling Step |
| title_sort | regularized particle filter with langevin resampling step |
| work_keys_str_mv | AT duanl regularizedparticlefilterwithlangevinresamplingstep AT farmerc regularizedparticlefilterwithlangevinresamplingstep AT morozi regularizedparticlefilterwithlangevinresamplingstep |