On an Adaptive Filter based on Simultaneous Perturbation Stochastic Approximation Method

In this paper, the simultaneous perturbation stochastic approximation (SPSA) algorithm is used for seeking optimal parameters in an adaptive filter developed for assimilating observations in very high dimensional dynamical systems. It is shown that the SPSA can achieve high performance similar to that produced by classical optimization algorithms, with better performance for non-linear filtering problems as more and more observations are assimilated. The advantage of the SPSA is that at each iteration it requires only two measurements of the objective function to approximate the gradient vector regardless of dimension of the control vector. This technique offers promising perspectives for future developement of optimal assimilation systems encountered in the field of data assimilation in meteorology and oceanography.