The Computational Complexity of Sensitivity Analysis and Parameter Tuning
Artificial Intelligence
2012-06-18 v1
Abstract
While known algorithms for sensitivity analysis and parameter tuning in probabilistic networks have a running time that is exponential in the size of the network, the exact computational complexity of these problems has not been established as yet. In this paper we study several variants of the tuning problem and show that these problems are NPPP-complete in general. We further show that the problems remain NP-complete or PP-complete, for a number of restricted variants. These complexity results provide insight in whether or not recent achievements in sensitivity analysis and tuning can be extended to more general, practicable methods.
Cite
@article{arxiv.1206.3265,
title = {The Computational Complexity of Sensitivity Analysis and Parameter Tuning},
author = {Johan Kwisthout and Linda C. van der Gaag},
journal= {arXiv preprint arXiv:1206.3265},
year = {2012}
}
Comments
Appears in Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI2008)