On the distribution of the conditional mean estimator in Gaussian noise
Document Type
Conference Proceeding
Publication Date
4-11-2021
Abstract
Consider the conditional mean estimator of the random variable X from the noisy observation Y = X + N where N is zero mean Gaussian with variance σ2 (i.e., E[X|Y ]). This work characterizes the probability distribution of E[X|Y ]. As part of the proof, several new identities and results are shown. For example, it is shown that the k-th derivative of the conditional expectation is proportional to the (k + 1)-th conditional cumulant. It is also shown that the compositional inverse of the conditional expectation is well-defined and is characterized in terms of a power series by using Lagrange inversion theorem.
Identifier
85106177792 (Scopus)
ISBN
[9781728159621]
Publication Title
2020 IEEE Information Theory Workshop Itw 2020
External Full Text Location
https://doi.org/10.1109/ITW46852.2021.9457595
Grant
CCF-1908308
Fund Ref
National Science Foundation
Recommended Citation
Dytso, Alex; Vincent Poor, H.; and Shamai, Shlomo, "On the distribution of the conditional mean estimator in Gaussian noise" (2021). Faculty Publications. 4181.
https://digitalcommons.njit.edu/fac_pubs/4181