Rate-distortion trade-offs in acquisition of signal parameters
Host Publication: IEEE International Conference on Acoustics, Speech, and Signal Processing
Authors: M. Rodrigues, N. Deligiannis, L. Lai and Y. Eldar
Publication Date: Mar. 2017
Number of Pages: 5
We consider problems where one wishes to represent a parameter associatedwith a signal source subject to a certain rate and distortion based on the observation of a number of realizations of the sourcesignal. By reducing these indirect vector quantization problems toa standard vector quantization one, we provide a bound to the fundamentalinterplay between the rate and distortion in the large-ratesetting. We specialize this characterization to two particular quantizationscenarios: i) the representation of the mean of a multivariateGaussian source and ii) the representation of the eigen-spectrumof a multivariate Gaussian source. Numerical results compare ourquantization approach to an approach where one recovers the parametersfrom the representation of the source signals itself: in additionto revealing that the characterization is sharp in the large-rate setting,the results also show that our approach offers considerable gains.