Worst-case source for distributed compression with quadratic distortion

Ilan Shomorony, Amir Salman Avestimehr, Himanshu Asnani, Tsachy Weissman

Abstract: We consider the k-encoder source coding problem with a quadratic distortion measure. We show that among all source distributions with a given covariance matrix K, the jointly Gaussian source requires the highest rates in order to meet a given set of distortion constraints.