Finite-memory algorithms for estimating the mean of a Gaussian distribution (Corresp.)

1 May 1974

journal article
Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory

Vol. 20 (3) , 382-384
https://doi.org/10.1109/tit.1974.1055229

Abstract

Let{X_n}_{n=1}^{infty}be independent random variables, each having amathcal{N}(mu, sigma^2)distribution. If we try to estimatemuwith anm-state learning algorithm, then the minimum mean-squared error is bounded below by that obtained by the bestm-level quantizer (which requires knowledge ofmu). Here we show that this lower bound is tight. The results are easily extended to a number of other problems, such as estimating the meanthetaof a uniform distribution.

Keywords

This publication has 15 references indexed in Scilit:

Optimal finite memory learning algorithms for the finite sample problem
Information and Control, 1976
A confidence model for finite-memory learning systems (Corresp.)
IEEE Transactions on Information Theory, 1972
The effects of randomization on finite-memory decision schemes
IEEE Transactions on Information Theory, 1972
On Memory Saved by Randomization
The Annals of Mathematical Statistics, 1971
Estimation with finite memory
IEEE Transactions on Information Theory, 1970
The two-armed-bandit problem with time-invariant finite memory
IEEE Transactions on Information Theory, 1970
Hypothesis Testing with Finite Statistics
The Annals of Mathematical Statistics, 1969
Randomized Rules for the Two-Armed-Bandit with Finite Memory
The Annals of Mathematical Statistics, 1968
Memory Limitation and Multistage Decision Processes
IEEE Transactions on Systems Science and Cybernetics, 1968
On Expediency and Convergence in Variable-Structure Automata
IEEE Transactions on Systems Science and Cybernetics, 1968