Greedy Importance Sampling
- Dale Schuurmans, AICML
I present a simple variation of importance sampling that explicitly search es for important regions in the target distribution. I prove that the tech nique yields unbiased estimates, and show empirically it can reduce the variance of standard Monte Carlo estimators. This is achieved by con centrating samples in more significant regions of the sample space.
Citation
D. Schuurmans. "Greedy Importance Sampling". Neural Information Processing Systems (NIPS), Denver, CO, USA, December 1999.Keywords: | importance, sampling, machine learning |
Category: | In Conference |
BibTeX
@incollection{Schuurmans:NIPS99, author = {Dale Schuurmans}, title = {Greedy Importance Sampling}, booktitle = {Neural Information Processing Systems (NIPS)}, year = 1999, }Last Updated: August 13, 2007
Submitted by Nelson Loyola