Maximum entropy performance analysis of spread-spectrum multiple-access communications

The Maximum Entropy Method (MEM) is used to evaluate the inter-user interference (IUI) probability distribution function (pdf) for Spread Spectrum Multiple Access (SSMA) systems. This pdf is frequently assumed to be Gaussian. We calculate the discrimination information (relative entropy) between the IUI-pdf as inferred via the MEM and the ''best'' Gaussian pdf in order to quantitatively assess the accuracy of the Gaussian assumption. We find that the Gaussian assumption becomes more accurate as the number of users increases. The widely used Gauss-Quadrature rule (GQR) based methods usually require a very high number of moments for accurate results and often fail for low error probabilities. The MEM results on the other hand require usually far fewer moments and continue to give accurate results in the practically important region of low error probabilities.