Sayed, Ali H.Al-Naffouri, Tareq Y.2017-12-192017-12-192017-12-19200110.1109/ICASSP.2001.940689https://infoscience.epfl.ch/handle/20.500.14299/142981We study leaky adaptive algorithms that employ a general scalar or matrix data nonlinearity. We perform mean-square analysis of this class of algorithms without imposing restrictions on the distribution of the input signal. In particular, we derive conditions on the step-size for stability, and provide closed form expressions for the steady-state performance.text::conference output::conference proceedings::conference paper