Technical Program

Paper Detail

Paper Title The CEO Problem with rth Power of Difference Distortion
Paper IdentifierTH2.R6.2
Authors Daewon Seo, Lav Varshney, University of Illinois at Urbana-Champaign, United States
Session Lossy Compression
Location Sorbonne, Level 5
Session Time Thursday, 11 July, 11:40 - 13:00
Presentation Time Thursday, 11 July, 12:00 - 12:20
Manuscript  Click here to download the manuscript
Abstract The CEO problem has received a lot of attention since Berger et al.~first investigated it, however, there are limited results on non-Gaussian models with non-quadratic distortion measures. In this work, we extend the CEO problem to two continuous-alphabet settings with general $r$th power of difference distortion, and study asymptotics of distortion as the number of agents and sum rate grow without bound. The first setting is a \emph{regular} source-observation model, such as jointly Gaussian, with difference distortion and we show that the distortion decays at $\Rsum^{-r/2}$ up to a multiplicative constant. The other setting is a \emph{non-regular} source-observation model, such as copula or uniform additive noise models, for which estimation-theoretic regularity conditions do not hold. The optimal decay $\Rsum^{-r}$ is obtained for the non-regular model.