Title :
Bounds on achievable convergence rates of parameter estimators via universal coding
Author_Institution :
Dept. of Electr. Eng., Technion-Israel Inst. of Technol., Haifa, Israel
fDate :
27 Jun-1 Jul 1994
Abstract :
Lower bounds on achievable convergence rates of parameter estimators towards the true parameter, are derived via universal coding considerations. It is shown that for a parametric class of sources, if there exists a universal lossless code whose redundancy decays sufficiently rapidly, then it induces a limitation on the fastest achievable convergence rate of any parameter estimator, at any value of the true parameter, with a possible exception of a vanishingly small subset of parameter values
Keywords :
convergence of numerical methods; parameter estimation; source coding; code redundancy; convergence rates; lower bounds; parameter estimators; source coding; universal coding; universal lossless code; Bayesian methods; Convergence; Entropy; Estimation error; Estimation theory; Mean square error methods; Parameter estimation; Random variables; Redundancy; Yield estimation;
Conference_Titel :
Information Theory, 1994. Proceedings., 1994 IEEE International Symposium on
Conference_Location :
Trondheim
Print_ISBN :
0-7803-2015-8
DOI :
10.1109/ISIT.1994.394935
