DMCA
Near-optimal nonmyopic value of information in graphical models (2005)
Cached
Download Links
| Venue: | IN ANNUAL CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE |
| Citations: | 144 - 24 self |
BibTeX
@INPROCEEDINGS{Krause05near-optimalnonmyopic,
author = {Andreas Krause and Carlos Guestrin},
title = {Near-optimal nonmyopic value of information in graphical models},
booktitle = {IN ANNUAL CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE},
year = {2005},
publisher = {John}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A fundamental issue in real-world systems, such as sensor networks, is the selection of observations which most effectively reduce uncertainty. More specifically, we address the long standing problem of nonmyopically selecting the most informative subset of variables in a graphical model. We present the first efficient randomized algorithm providing a constant factor (1 − 1/e − ε) approximation guarantee for any ε> 0 with high confidence. The algorithm leverages the theory of submodular functions, in combination with a polynomial bound on sample complexity. We furthermore prove that no polynomial time algorithm can provide a constant factor approximation better than (1 − 1/e) unless P = NP. Finally, we provide extensive evidence of the effectiveness of our method on two complex real-world datasets.
Keyphrases
graphical model near-optimal nonmyopic value polynomial time algorithm approximation guarantee polynomial bound real-world system sample complexity constant factor approximation extensive evidence fundamental issue constant factor high confidence complex real-world datasets sensor network long standing problem informative subset submodular function
