Heretical Multiple Importance Sampling
arXiv:1609.04740 · doi:10.1109/LSP.2016.2600678
Abstract
Multiple Importance Sampling (MIS) methods approximate moments of complicated distributions by drawing samples from a set of proposal distributions. Several ways to compute the importance weights assigned to each sample have been recently proposed, with the so-called deterministic mixture (DM) weights providing the best performance in terms of variance, at the expense of an increase in the computational cost. A recent work has shown that it is possible to achieve a trade-off between variance reduction and computational effort by performing an a priori random clustering of the proposals (partial DM algorithm). In this paper, we propose a novel "heretical" MIS framework, where the clustering is performed a posteriori with the goal of reducing the variance of the importance sampling weights. This approach yields biased estimators with a potentially large reduction in variance. Numerical examples show that heretical MIS estimators can outperform, in terms of mean squared error (MSE), both the standard and the partial MIS estimators, achieving a performance close to that of DM with less computational cost.
8 pages, 2 figures
References in corpus (4)
Cited by in corpus (12)
- A Survey of Monte Carlo Methods for Parameter Estimation
- Generalized Multiple Importance Sampling
- Marginal likelihood computation for model selection and hypothesis testing: an extensive review
- Group Importance Sampling for Particle Filtering and MCMC
- Importance Gaussian Quadrature
- Implicitly Adaptive Importance Sampling
- Robust Covariance Adaptation in Adaptive Importance Sampling
- Metropolis Sampling
- Multiple Importance Sampling for Efficient Symbol Error Rate Estimation
- MCMC-driven importance samplers
- Hamiltonian Adaptive Importance Sampling
- Advances in Importance Sampling