Title :
On the training distortion of vector quantizers
Author_Institution :
Dept. of Math. & Stat., Queen´´s Univ., Kingston, Ont., Canada
Abstract :
The in-training-set performance of a vector quantizer as a function of its training set size is investigated. For squared error distortion and independent training data, worst-case type upper bounds are derived on the minimum training distortion achieved by an empirically optimal quantizer. These bounds show that the training distortion can underestimate the minimum distortion of a truly optimal quantizer by as much as a constant times n-1/2, where n is the size of the training data. Earlier results provide lower bounds of the same order
Keywords :
minimax techniques; source coding; vector quantisation; empirically optimal quantizer; in-training-set performance; independent training data; lower bounds; minimax bounds; minimum distortion; source distribution; squared error distortion; training distortion; training set size; vector quantizers; worst-case type upper bounds; Algorithm design and analysis; Distortion measurement; Mathematics; Minimax techniques; Power engineering and energy; Q measurement; Statistics; Testing; Training data; Upper bound;
Conference_Titel :
Information Theory, 2000. Proceedings. IEEE International Symposium on
Conference_Location :
Sorrento
Print_ISBN :
0-7803-5857-0
DOI :
10.1109/ISIT.2000.866443
