Open Access
Translator Disclaimer
2022 The least favorable noise
Philip A. Ernst, Abram M. Kagan, L.C.G. Rogers
Author Affiliations +
Electron. Commun. Probab. 27: 1-11 (2022). DOI: 10.1214/22-ECP467

Abstract

Suppose that a random variable X of interest is observed perturbed by independent additive noise Y. This paper concerns the “the least favorable perturbation” Yˆε, which maximizes the prediction error E(XE(X|X+Y))2 in the class of Y with var(Y)ε. We find a characterization of the answer to this question, and show by example that it can be surprisingly complicated. However, in the special case where X is infinitely divisible, the solution is complete and simple. We also explore the conjecture that noisier Y makes prediction worse.

Dedication

We dedicate this work to our colleague, mentor, and friend, Professor Larry Shepp (1936–2013)

Acknowledgments

We thank Professor Dan Crisan (Imperial College London) and Dongzhou Huang (Rice University) for helpful discussions. We also wish to thank an anonymous referee whose helpful and detailed comments have greatly improved the quality of this manuscript. The first-named author gratefully acknowledges the support of ARO-YIP-71636-MA, NSF DMS-1811936, ONR N00014-18-1-2192, and ONR N00014-21-1-2672.

Citation

Download Citation

Philip A. Ernst. Abram M. Kagan. L.C.G. Rogers. "The least favorable noise." Electron. Commun. Probab. 27 1 - 11, 2022. https://doi.org/10.1214/22-ECP467

Information

Received: 18 March 2021; Accepted: 16 April 2022; Published: 2022
First available in Project Euclid: 17 May 2022

Digital Object Identifier: 10.1214/22-ECP467

Subjects:
Primary: 60E07 , 60E10
Secondary: 60E05

Keywords: Infinitely divisible distributions , least favorable perturbation , self-decomposable random variable

JOURNAL ARTICLE
11 PAGES


SHARE
Back to Top