UNBIASED PARAMETER ESTIMATION FOR PARTIALLY OBSERVED DIFFUSIONS

In this article we consider the estimation of static parameters for a partially observed diffusion process with discrete-time observations over a fixed time interval. In particular, we assume that one must time-discretize the partially observed diffusion process and work with the model with bias and consider maximizing the resulting log-likelihood. Using a novel double randomization scheme, based upon Markovian stochastic approximation we develop a new method to, in principle, unbiasedly estimate the static parameters, that is, to obtain the maximum likelihood estimator with no time discretization bias. Under appropriate mathematical assumptions we prove that our estimator is unbiased and investigate the method in several numerical examples, showing that it can empirically outperform the unbiased method in [J. Heng, J. Houssineau, and A. Jasra, J. Mach. Learn. Res ., 25 (2024)].