GAUSSIAN PROCESSES FOR REGRESSION IN CHANNEL EQUALIZATION

Linear equalizers underperform in dispersive channels with additive white noise, because optimal decision functions are nonlinear. In this paper we present Gaussian Processes (GPs) for regression as new nonlinear equalizer for digi-tal communication systems. GPs can be cast as nonlin-ear MMSE, a commom criterion in digital communications. Unlike other nonlinear kernel based methods, such as ker-nel adaline or support vector machines, the solutions pro-duced by GPs are analytical, and the hyperparameters can be readily learnt by maximum likelihood. Hence, we avoid cross-validation or noise estimation, and improve conver-gence speed. We present experimental results, over linear and nonlinear channel models, to show that GP-equalizers outperform linear and nonlinear state-of-the-art solutions. 1