Title :
The minimax distortion redundancy in empirical quantizer design
Author :
Bartlett, Peter ; Linder, Tamás ; Lugosi, Gábor
Author_Institution :
Dept. of Syst. Eng., Australian Nat. Univ., Canberra, ACT, Australia
fDate :
29 Jun-4 Jul 1997
Abstract :
We prove that the minimax expected squared distortion redundancy in designing vector quantizers from n independent training vectors is of the order of n-1/2
Keywords :
minimax techniques; rate distortion theory; redundancy; vector quantisation; data compression; empirical quantizer design; independent training vectors; minimax expected squared distortion redundancy; source statistics; vector quantizers; Data compression; Distortion measurement; Euclidean distance; Minimax techniques; Q measurement; Rate distortion theory; Statistics; Systems engineering and theory; Training data; Upper bound;
Conference_Titel :
Information Theory. 1997. Proceedings., 1997 IEEE International Symposium on
Conference_Location :
Ulm
Print_ISBN :
0-7803-3956-8
DOI :
10.1109/ISIT.1997.613448
