Abstract
In this paper, we prove Lp-convergence for p > 1 of the particle filter for a class of unbounded functions. Furthermore, it can be shown that the approximation solution converges in probability to the true optimal estimate for the case 1 < p ≤ 2 and the approximation solution converges almost surely to the true optimal estimate for the case p > 2. In addition, some numerical experiments are presented to illustrate the main convergence results.
| Original language | English |
|---|---|
| Pages (from-to) | 1309-1318 |
| Number of pages | 10 |
| Journal | Journal of Computational Analysis and Applications |
| Volume | 13 |
| Issue number | 7 |
| State | Published - 2011 |
Keywords
- Bayesian estimation
- Conditional expectation
- Particle filter
- Probability density function
Fingerprint
Dive into the research topics of 'Lp(p > 1) convergence results for particle filtering'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver