TY - GEN
T1 - The CEO Problem with rth Power of Difference Distortion
AU - Seo, Daewon
AU - Varshney, Lav R.
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/7
Y1 - 2019/7
N2 - 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 rth 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 regular source-observation model, such as jointly Gaussian, with difference distortion and we show that the distortion decays at R ∑ r/2 up to a multiplicative constant. The other setting is a 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 R-rsum is obtained for the non-regular model.
AB - 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 rth 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 regular source-observation model, such as jointly Gaussian, with difference distortion and we show that the distortion decays at R ∑ r/2 up to a multiplicative constant. The other setting is a 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 R-rsum is obtained for the non-regular model.
UR - http://www.scopus.com/inward/record.url?scp=85073147966&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85073147966&partnerID=8YFLogxK
U2 - 10.1109/ISIT.2019.8849701
DO - 10.1109/ISIT.2019.8849701
M3 - Conference contribution
AN - SCOPUS:85073147966
T3 - IEEE International Symposium on Information Theory - Proceedings
SP - 2034
EP - 2038
BT - 2019 IEEE International Symposium on Information Theory, ISIT 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE International Symposium on Information Theory, ISIT 2019
Y2 - 7 July 2019 through 12 July 2019
ER -