\(\DeclarePairedDelimiterX{\Set}[2]{\{}{\}}{#1 \nonscript\;\delimsize\vert\nonscript\; #2}\) \( \DeclarePairedDelimiter{\set}{\{}{\}}\) \( \DeclarePairedDelimiter{\parens}{\left(}{\right)}\) \(\DeclarePairedDelimiterX{\innerproduct}[1]{\langle}{\rangle}{#1}\) \(\newcommand{\ip}[1]{\innerproduct{#1}}\) \(\newcommand{\bmat}[1]{\left[\hspace{2.0pt}\begin{matrix}#1\end{matrix}\hspace{2.0pt}\right]}\) \(\newcommand{\barray}[1]{\left[\hspace{2.0pt}\begin{matrix}#1\end{matrix}\hspace{2.0pt}\right]}\) \(\newcommand{\mat}[1]{\begin{matrix}#1\end{matrix}}\) \(\newcommand{\pmat}[1]{\begin{pmatrix}#1\end{pmatrix}}\) \(\newcommand{\mathword}[1]{\mathop{\textup{#1}}}\)
Needs:
Multivariate Normals
Tree Densities
Needed by:
Tree Approximators of a Normal
Links:
Sheet PDF
Graph PDF

Tree Normals

Why

We name multivariate normal densities which factor according to a tree. These densities require tabulating fewer numbers.

Definition

A tree multivariate normal (or tree normal, tree gaussian) density is a multivariate normal density which factors according to a tree.

Fewer numbers

A multivariate normal on $\R ^n$ requires tabulating $n$ numbers for the mean and $n(n+1)/2$ numbers for the covariance matrix. If it factors according to a tree, we need only $n$ numbers to specify the covariance (one for the one-variable marginal, and $n-1$ for the covariance of the two-variable conditionals).

Copyright © 2023 The Bourbaki Authors — All rights reserved — Version 13a6779cc About Show the old page view