Importance sampling with transformed weights Articles
Overview
published in
- ELECTRONICS LETTERS Journal
publication date
- July 2017
start page
- 783
end page
- 784
issue
- 12
volume
- 53
Digital Object Identifier (DOI)
full text
International Standard Serial Number (ISSN)
- 0013-5194
Electronic International Standard Serial Number (EISSN)
- 1350-911X
abstract
- The importance sampling (IS) method lies at the core of many Monte Carlo-based techniques. IS allows the approximation of a target probability distribution by drawing samples from a proposal (or importance) distribution, different from the target, and computing importance weights (IWs) that account for the discrepancy between these two distributions. The main drawback of IS schemes is the degeneracy of the IWs, which significantly reduces the efficiency of the method. It has been recently proposed to use transformed IWs (TIWs) to alleviate the degeneracy problem in the context of population Monte Carlo, which is an iterative version of IS. However, the effectiveness of this technique for standard IS is yet to be investigated. The performance of IS when using TIWs is numerically assessed, and showed that the method can attain robustness to weight degeneracy thanks to a bias/variance trade-off.
Classification
subjects
- Statistics
keywords
- importance sampling; statistical distributions; importance weights; probability distribution; monte carlo-based techniques; transformed weights