Nonlinear filtering : Interacting particle resolution

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Filtering Complex Turbulent Systems (2012, background): “When the system is low dimensional or when it has a low dimensional attractor, MonteCarlo approaches such as the particle filter [25] with its various up-to-date resampling strategies [35, 36, 119] provide better estimates in the presence of strong nonlinearity and highly non-Gaussian distributions.”
Branching and interacting particle systems. Approximations of Feynman-Kac formulae with applications to non-linear filtering (2000, background): “1 ([30]) For any 0 p nand f e Bb(E) we have that ~~~~ ~~~~ p,n > ~”
Towards Automatic Model Comparison: An Adaptive Sequential Monte Carlo Approach (2013, methodology): “See Del Moral et al. (2006b) for details on calculating the incremental weights in general; in practice, when K n is π n -invariant, π n π n − 1 , and is used as the backward kernel, the unnormalised incremental weights become This will be the situation throughout the remainder of this paper.”
An Overview of Existing Methods and Recent Advances in Sequential Monte Carlo (2007, methodology): “Since then, there have been several independent variants of similar filtering ideas, including the Condensation filter [17], Monte Carlo filter [1], Sequential imputations [18], and the Particle filter [19].”