On Stochastic Stability of a Class of non-Markovian Processes and Applications in Quantization
arXiv:1612.06988 · doi:10.1137/140984154
Abstract
In many applications, the common assumption that a driving noise process affecting a system is independent or Markovian may not be realistic, but the noise process may be assumed to be stationary. To study such problems, this paper investigates stochastic stability properties of a class of non-Markovian processes, where the existence of a stationary measure, asymptotic mean stationarity and ergodicity conditions are studied. Applications in feedback quantization and stochastic control are presented.
arXiv commentA clarification in the statement of Theorem 3.9 (on Assumption 2.3 for the applications)