Title :
On the selection of optimal nonlinearities for stochastic gradient adaptive algorithms
Author :
Al-Naffouri, Tareqy ; Sayed, Ali H. ; Kailath, Thomas
Author_Institution :
Dept. of Electr. Eng., Stanford Univ., CA, USA
Abstract :
This paper derives an expression for the optimal error nonlinearity in adaptive filter design. Using an energy conservation relation, and some typical assumptions, the choice of the error function is optimized by minimizing the mean-square deviation subject to a fixed rate of convergence. The resulting optimal choice is shown to subsume earlier results as special cases
Keywords :
adaptive filters; adaptive signal processing; convergence of numerical methods; filtering theory; gradient methods; least mean squares methods; optimisation; stochastic processes; adaptive filter design; energy conservation relation; error function; fixed convergence rate; mean-square deviation minimization; optimal error nonlinearity; optimal nonlinearities selection; second-order analysis; stochastic gradient adaptive algorithms; Adaptive algorithm; Adaptive filters; Algorithm design and analysis; Design engineering; Energy conservation; Estimation error; Noise measurement; Power engineering and energy; Steady-state; Stochastic processes;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on
Conference_Location :
Istanbul
Print_ISBN :
0-7803-6293-4
DOI :
10.1109/ICASSP.2000.862014
