Interior moment matching in a finite exponential family
= Interior moment matching in a finite exponential family
{title2=$\nabla\log\sum_ne^{\theta\cdot n}=\mu$}
For a finite support whose <convex hull> has full dimension, every interior target mean is realized by a unique natural parameter. Minimize the <coercive function> $\log\sum_ne^{\theta\cdot n}-\theta\cdot\mu$; its <gradient> is the mean discrepancy and its <Hessian matrix> is the positive-definite <covariance matrix> of the support.