Abstract
Multiple importance sampling (MIS) methods use a set of proposal distributions from which samples are drawn. Each sample is then assigned an importance weight that can be obtained according to different strategies. This work is motivated by the trade-off between variance reduction and computational complexity of the different approaches (classical vs. deterministic mixture) available for the weight calculation. A new method that achieves an efficient compromise between both factors is introduced in this letter. It is based on forming a partition of the set of proposal distributions and computing the weights accordingly. Computer simulations show the excellent performance of the associated partial deterministic mixture MIS estimator.
Original language | English |
---|---|
Article number | 7105865 |
Pages (from-to) | 1757-1761 |
Number of pages | 5 |
Journal | IEEE Signal Processing Letters |
Volume | 22 |
Issue number | 10 |
Early online date | 12 May 2015 |
DOIs | |
Publication status | Published - 1 Oct 2015 |
Keywords / Materials (for Non-textual outputs)
- Adaptive importance sampling
- Deterministic mixture
- Monte Carlo methods
- Multiple importance sampling