Finite-Sample Maximum Likelihood Estimation of Location
Gupta, Shivam, Lee, Jasper C. H., Price, Eric, Valiant, Paul
–arXiv.org Artificial Intelligence
We consider 1-dimensional location estimation, where we estimate a parameter $\lambda$ from $n$ samples $\lambda + \eta_i$, with each $\eta_i$ drawn i.i.d. from a known distribution $f$. For fixed $f$ the maximum-likelihood estimate (MLE) is well-known to be optimal in the limit as $n \to \infty$: it is asymptotically normal with variance matching the Cram\'er-Rao lower bound of $\frac{1}{n\mathcal{I}}$, where $\mathcal{I}$ is the Fisher information of $f$. However, this bound does not hold for finite $n$, or when $f$ varies with $n$. We show for arbitrary $f$ and $n$ that one can recover a similar theory based on the Fisher information of a smoothed version of $f$, where the smoothing radius decays with $n$.
arXiv.org Artificial Intelligence
Jul-18-2022
- Country:
- North America > United States
- Wisconsin > Dane County
- Madison (0.04)
- Texas > Travis County
- Austin (0.04)
- California > Alameda County
- Berkeley (0.04)
- Wisconsin > Dane County
- Europe > United Kingdom
- England
- Oxfordshire > Oxford (0.04)
- Cambridgeshire > Cambridge (0.04)
- England
- North America > United States
- Genre:
- Research Report (1.00)