A Comparison of Traditional and Deep Learning Methods for Parameter Estimation of the Ornstein-Uhlenbeck Process
This addresses parameter estimation challenges in fields like finance, physics, and biology, but is incremental as it applies an existing deep learning method to a known problem.
The paper tackles parameter estimation for the Ornstein-Uhlenbeck process by comparing traditional methods like Kalman filter and maximum likelihood with a novel deep learning approach using a multi-layer perceptron, finding that the deep learning method outperforms traditional ones on average with accurate estimates given large datasets.
We consider the Ornstein-Uhlenbeck (OU) process, a stochastic process widely used in finance, physics, and biology. Parameter estimation of the OU process is a challenging problem. Thus, we review traditional tracking methods and compare them with novel applications of deep learning to estimate the parameters of the OU process. We use a multi-layer perceptron to estimate the parameters of the OU process and compare its performance with traditional parameter estimation methods, such as the Kalman filter and maximum likelihood estimation. We find that the multi-layer perceptron can accurately estimate the parameters of the OU process given a large dataset of observed trajectories and, on average, outperforms traditional parameter estimation methods.