Minimum variance importance sampling via Population Monte Carlo

By Randal Douc, Arnaud Guillin, Jean-Michel Marin, Christian P. Robert. 2007

102 citations recorded by the source corpus.

Subfields: Finance, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/db8d4098b044ba3b3979bfa0fdc3da1c0d249fcf

How researchers see this paper

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

In Finance

In Statistics and Probability

Citations in the corpus

Adaptive Multiple Importance Sampling (2009, background): “…poorly performing proposal, while the qls (l > 1) are good approximations of , for a value y0i such that (y0i )/q0(y 0 i ) is large, because q0(y 0 i ) is small, (y 0 i )/{N0q0(y0i )+ · · ·+NT qT (y0i )} will behave like (y0i )/{N1q1(y0i )+ · · ·+NT qT (y0i )} and decrease to zero as T increases.”
Exact and computationally efficient likelihood‐based estimation for discretely observed diffusion processes (with discussion) (2006, methodology): “For instance, in the simulation of the Cox–Ingersoll–Ross model, importance functions that introduce a drift in the variance of expression (30) lead to a significant improvement in the estimation of some quantities (Douc et al., 2005).”
Zero variance Markov chain Monte Carlo for Bayesian estimators (2010, methodology): “To demonstrate the effectiveness of ZV in this setting, a simple example, Douc et al. (2007), is presented.”
An Overview of Existing Methods and Recent Advances in Sequential Monte Carlo (2007, background): “αm are the parameters of the proposal to be adapted are given in [112], [113].”
An Adaptive Sequential Monte Carlo Sampler (2010, background): “Sections 2.1 and 2.2 provide a brief description of two such Monte Carlo approaches.”
Generalized Multiple Importance Sampling (2015, methodology): “MIS scheme Function φj,t(x) N P L Corresponding Algorithm LP = N N1 qj,t(x) JT 1 PMC [8] Full N3 ψ(x) = 1 JT ∑J j=1 ∑T t=1 qj,t(x) 1 JT suggested in [7] Partial (temporal) N3 ξj(x) = 1 T ∑T t=1 qj,t(x) JT J T AMIS [11], with J = 1 Partial (spatial) N3 φt(x) = 1 J ∑J j=1 qj,t(x) T J APIS [10] Partial”
Adaptive importance sampling in general mixture classes (2007, methodology): “…one above upon replacing ξ i,t by its conditional expectation Note that, as discussed in Section 2.2, establishing the convergence of the parameter update in this Gaussian setting will only require the assumption that ρ d ( x ; α, θ ) x 2 is integrable with respect to π (see Douc et al., 2007a).”