= Differentiability in quadratic mean
{title2=$\|\sqrt{p_t}-\sqrt p-\tfrac t2g\sqrt p\|_2=o(|t|)$}
= Differentiable in quadratic mean
{synonym}
= Differentiable-in-quadratic-mean path
{synonym}
= DQM
{c}
{synonym}
A dominated <statistical path> is differentiable in quadratic mean at $P$ if its square-root <probability density function> has an <L2 space> <derivative> $(1/2)g\sqrt p$, with $g\in L^2(P)$. The <score function> is $g$. This formulation controls mass near zeros of $p$ as well as the <derivative> on the support of $P$; a pointwise log-density <derivative> is insufficient by itself.
Back to article page
