KL-divergence between two products

Given factorizations of two joint densities $p(x_1,...,x_n)=\prod_{i=1}^n p(x_i\mid \textrm{cond}(x_i))$ and $q(x_1,...,x_n)=\prod_{i=1}^n q(x_i\mid \textrm{cond}(x_i))$, where $\textrm{cond}(\bullet)$ denotes the set of conditioning variables, does the KL-divergence decompose, i.e., does

$\textrm{KL}(p\Vert q)= \sum_{i=1}^n \textrm{KL}\left(p(x_i\mid \textrm{cond}(x_i))\ \Vert\ q(x_i\mid \textrm{cond}(x_i))\right)$

hold?

• If it makes things easier, you can assume $\textrm{cond}(x_i) \in \{x_1,\ldots,x_n\}$ . More generally, the two factorisations are Bayesian networks, which means that $\textrm{cond}(x_i)$ can be any subset of $\{x_1,\ldots,x_n\}$ so that the induced graph structure is a directed acyclic graph. – ASML Jan 23 '16 at 14:23
• How do you define $\textrm{KL}\left(p(x_i\mid \textrm{cond}(x_i))\ \Vert\ q(x_i\mid \textrm{cond}(x_i))\right)$ ? The ambiguous part is how you integrate out the $cond(x_i)$ variables in there – Guillaume Dehaene Feb 3 '16 at 13:42