System identification under non-negativity constraints

Dynamic system modeling plays a crucial role in the development of techniques for stationary and non-stationary signal processing. Due to the inherent physical characteristics of systems usually under investigation, non-negativity is a desired constraint that can be imposed on the parameters to estimate. In this paper, we propose a general method for system identification under non-negativity constraints. We derive additive and multiplicative weight update algorithms, based on (stochastic) gradient descent of mean-square error or Kullback-Leibler divergence. Experiments are conducted to validate the proposed approach.