EMPIRICAL QUANTIZER DESIGN IN THE PRESENCE OF SOURCE NOISE OR CHANNELNOISE

The problem of vector quantizer empirical design for noisy channels or for noisy sources is studied, It is shown that the average squared di stortion of a vector quantizer designed optimally from observing clean independent and identically distributed (i.i.d.) training vectors con verges in expectation, as the training set size grows, to the minimum possible mean-squared error obtainable for quantizing the clean source and transmitting across a discrete memoryless noisy channel, Similarl y, it is shown that if the source is corrupted by additive noise, then the average squared distortion of a vector quantizer designed optimal ly from observing i.i.d. noisy training vectors converges in expectati on, as the training set size grows, to the minimum possible mean-squar ed error obtainable for quantizing the noisy source and transmitting a cross a noiseless channel, Rates of convergence are also provided.