Measure Concentration of Markov Tree Processes
Probability
2007-05-23 v5 Functional Analysis
Abstract
We prove an apparently novel concentration of measure result for Markov tree processes. The bound we derive reduces to the known bounds for Markov processes when the tree is a chain, thus strictly generalizing the known Markov process concentration results. We employ several techniques of potential independent interest, especially for obtaining similar results for more general directed acyclic graphical models.
Cite
@article{arxiv.math/0608511,
title = {Measure Concentration of Markov Tree Processes},
author = {Leonid Kontorovich},
journal= {arXiv preprint arXiv:math/0608511},
year = {2007}
}
Comments
14 pages