General Lower Bounds based on Computer Generated Higher Order Expansions
Numerical Analysis
2013-01-07 v1
Abstract
In this article we show the rough outline of a computer algorithm to generate lower bounds on the exponential function of (in principle) arbitrary precision. We implemented this to generate all necessary analytic terms for the Boltzmann machine partition function thus leading to lower bounds of any order. It turns out that the extra variational parameters can be optimized analytically. We show that bounds upto nineth order are still reasonably calculable in practical situations. The generated terms can also be used as extra correction terms (beyond TAP) in mean field expansions.
Cite
@article{arxiv.1301.0581,
title = {General Lower Bounds based on Computer Generated Higher Order Expansions},
author = {Martijn Leisink and Hilbert Kappen},
journal= {arXiv preprint arXiv:1301.0581},
year = {2013}
}
Comments
Appears in Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence (UAI2002)