Kernel-based learning method for interacting particle systems and its mean field limit
speaker: Chiara Segala (RTWH Aachen)abstract: Kernel methods, being supported by a well-developed theory and coming with efficient algorithms, are among the most popular and successful machine learning techniques. From a mathematical point of view, these methods rest on the concept of kernels and function spaces generated by kernels, so–called reproducing kernel Hilbert spaces. Motivated by recent developments of learning approaches in the context of interacting particle systems, we investigate kernel methods acting on data with many measurement variables. In particular, when treating numerical methods for simulation and optimization aspects, the efficient simulation of those systems is still challenging and kernel methods have been proposed to approximate them. We show the rigorous mean field limit of kernels and provide numerical evidence of their efficacy for a variety of interacting agent systems.
timetable:
Tue 23 Jan, 11:10 - 12:00, Aula Dini
<< Go back