Reducing parameter optimization uncertainties of dynamic models by meta- learning (C03)

• Subject Area: Epidemiology and Medical Biometry/Statistics ; Statistical Physics, Nonlinear Dynamics, Complex Systems, Soft and Fluid Matter, Biological Physics
• Term: since 2023
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 499552394

To reduce the parameter optimization uncertainty of ordinary differential equations, we are going to develop a meta-learning approach that learns to solve an optimization task at hand from preceding optimization steps and similar other optimization problems. Specifically, we will consider how different optimization methods perform in solving publicly available problems to derive a default policy in the form of actions that choose the best optimization method. For a new optimization task, this policy will be adapted automatically via reinforcement learning.

• DFG Programme: Collaborative Research Centres
• Subproject of: SFB 1597: Small Data
• Applicant Institution: Albert-Ludwigs-Universität Freiburg
• Project Heads: Dr. Clemens Kreutz; Professor Dr. Jens Timmer