Means, Correlations and Bounds
Abstract
The partition function for a Boltzmann machine can be bounded from above and below. We can use this to bound the means and the correlations. For networks with small weights, the values of these statistics can be restricted to non-trivial regions (i.e. a subset of [-1 , 1]). Experimental results show that reasonable bounding occurs for weight sizes where mean field expansions generally give good results.
Cite
Text
Leisink and Kappen. "Means, Correlations and Bounds." Neural Information Processing Systems, 2001.Markdown
[Leisink and Kappen. "Means, Correlations and Bounds." Neural Information Processing Systems, 2001.](https://mlanthology.org/neurips/2001/leisink2001neurips-means/)BibTeX
@inproceedings{leisink2001neurips-means,
title = {{Means, Correlations and Bounds}},
author = {Leisink, Martijn and Kappen, Bert},
booktitle = {Neural Information Processing Systems},
year = {2001},
pages = {455-462},
url = {https://mlanthology.org/neurips/2001/leisink2001neurips-means/}
}