Under regularity conditions plus assumptions on the score, the normalized MLE has sub-Gaussian tails, all moments converge, and the estimator converges in relative entropy to Gaussian when Fisher information is bounded or the density has bounded derivative.
On the assumptions used to prove asymptotic normality of maximum likelihood estimates,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sub-Gaussian Concentration and Entropic Normality of the Maximum Likelihood Estimator
Under regularity conditions plus assumptions on the score, the normalized MLE has sub-Gaussian tails, all moments converge, and the estimator converges in relative entropy to Gaussian when Fisher information is bounded or the density has bounded derivative.