Skip to main content

Finite-Sample Bounds on the Accuracy of Plug-In Estimators of Fisher Information

Author(s): Cao, Wei; Dytso, Alex; Fauss, Michael; Poor, H. Vincent

To refer to this page use:
Abstract: Finite-sample bounds on the accuracy of Bhattacharya’s plug-in estimator for Fisher information are derived. These bounds are further improved by introducing a clipping step that allows for better control over the score function. This leads to superior upper bounds on the rates of convergence, albeit under slightly different regularity conditions. The performance bounds on both estimators are evaluated for the practically relevant case of a random variable contaminated by Gaussian noise. Moreover, using Brown’s identity, two corresponding estimators of the minimum mean-square error are proposed.
Electronic Publication Date: 28-Apr-2021
Citation: Cao, Wei, Dytso, Alex, Fauß, Michael, Poor, H Vincent. (Finite-Sample Bounds on the Accuracy of Plug-In Estimators of Fisher Information. Entropy, 23 (5), 545 - 545. doi:10.3390/e23050545
DOI: doi:10.3390/e23050545
EISSN: 1099-4300
Pages: 545 - 545
Language: en
Type of Material: Journal Article
Journal/Proceeding Title: Entropy
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.