Al-Naffouri, Tareq YSayed, Ali H.2017-12-192017-12-192017-12-19200210.1109/ICASSP.2002.5744885https://infoscience.epfl.ch/handle/20.500.14299/143236In this paper, we consider the class of adaptive filters with error nonlinearities. In particular, we derive an expression for the optimum nonlinearity that minimizes the steady-state error and attains the limit mandated by the Cramer-Rae bound of the underlying estimation process.text::conference output::conference proceedings::conference paper