Title :
Multiterminal estimation - extensions and geometric interpretation
Author :
Jörnsten, Rebecka ; Yu, Bin
Author_Institution :
Dept. of Stat., Rutgers Univ., Piscataway, NJ, USA
Abstract :
There are two approaches to establishing estimation efficiency bounds in a multiterminal setting. Zhang and Berger (see IEEE Trans. Inf. Theory, vol.34, no.2, p.198-211, 1988) derive a bound using the so-called solvability conditions. Han and Amari (see IEEE Trans. Inf. Theory, vol.41, no.6, p.1802-33, 1995) tighten the bound under weaker rate and test channel constraints, but their bound is prohibitively complex to compute. Here we construct a bound that is asymptotically equal to the Han and Amari bound, yet easily computed and has a geometric interpretation.
Keywords :
encoding; information theory; parameter estimation; channel constraints; encoding functions; estimation efficiency bounds; geometric interpretation; multiterminal estimation; solvability conditions; Code standards; Entropy; Equations; Maximum likelihood decoding; Maximum likelihood estimation; Statistical distributions; Statistics; Testing;
Conference_Titel :
Information Theory, 2002. Proceedings. 2002 IEEE International Symposium on
Print_ISBN :
0-7803-7501-7
DOI :
10.1109/ISIT.2002.1023296