Research

The proposed project focus on the design and validation of statistical inference methods and their application to study dynamic properties of complex stochastic systems.

Specifically, we study numerical methods for inference with stochastic differential equations (SDEs), focusing on Variational inference, Maximum Likelihood Estimation (MLE) and Bayesian inference.

Complex stochastic systems describe a variety of physico-chemical phenomena. In the current project, we apply the statistical inference methods (a) complex molecular systems, to reveal and validate kinetic properties of such models across scales, in a parametric formulation of SDE's.

The project aims to the application of statistical, data-driven, methods and to build effective models that describe dynamic properties of stochastic systems.