Maximum likelihood based multi-innovation stochastic gradient estimation for controlled autoregressive ARMA systems using the data filtering technique

This paper considers parameter estimation problems of a controlled autoregressive ARMA system. We decompose this system into two subsystems, use the data filtering technique to derive a maximum likelihood multi-innovation stochastic gradient algorithm. The simulation results show that the proposed algorithm has a higher computational efficiency than the maximum likelihood gradient algorithm and the filtering-based maximum likelihood stochastic gradient algorithm.