SearchSkip to Search Results
- 2Central Limit Theorem
- 2Particle filters
- 1Bayesian Model Selection
- 1Branching Process
- 1Exchangeable Random Variables
We introduce two kinds of particle filters, one is weighted particle filter and the other is resampling particle filter. We prove the Strong Law of Large Numbers and Central Limit Theorem for both particle filters. Then, we show that the resampling particle filter is better than the weighted one.
A large class of discrete-time branching particle ﬁlters with Bayesian model selection ca-pabilities and eﬀective resampling is introduced in algorithmic form, shown empirically to outperform the popular bootstrap algorithm and analyzed mathematically. The particles interact weakly in the...