A New Stochastic Approximation Method for Gradient-based Simulated Parameter Estimation
This provides a robust solution for parameter estimation in complex stochastic models like hidden Markov models, though it appears incremental as an extension of the GSPE framework.
The paper tackles parameter calibration in stochastic models with unavailable likelihood functions by introducing a gradient-based simulated parameter estimation framework using a multi-time scale stochastic approximation algorithm. The method enhances estimation accuracy and reduces computational costs, as shown in numerical experiments.
This paper tackles the challenge of parameter calibration in stochastic models, particularly in scenarios where the likelihood function is unavailable in an analytical form. We introduce a gradient-based simulated parameter estimation framework, which employs a multi-time scale stochastic approximation algorithm. This approach effectively addresses the ratio bias that arises in both maximum likelihood estimation and posterior density estimation problems. The proposed algorithm enhances estimation accuracy and significantly reduces computational costs, as demonstrated through extensive numerical experiments. Our work extends the GSPE framework to handle complex models such as hidden Markov models and variational inference-based problems, offering a robust solution for parameter estimation in challenging stochastic environments.