|
Abstract:
|
Cappe et al. (2004) proposed a simulation scheme dubbed Population Monte Carlo which may be viewed as an Iterated Importance Sampling approach, with resampling and Markovian instrumental simulations. This scheme also is a particular case of the Sequential Monte Carlo Sampling approach of Delmoral et al. (2006), although we focus on the case where the target distribution is held fixed and the importance kernels are adapted during the iterations in order to optimize a performance criterion. In Douc et al. (2006), we established convergence properties of specific adaptation schemes in terms of entropy and variance improvements. The talk will cover recent developments based on preliminary clustering and tempering steps, obtained jointly with J.M. Marin and A. Mira, as well as applications to cosmological issues.
|
