Mini-Workshop: High-Dimensional Control Problems and Mean-Field Equations with Applications in Machine Learning

Oberwolfach Reports, vol. 21, pp. 3211–3254

Abstract

High-dimensional control problems and mean field equations have been of increased interest in recent years and novel numerical tools tackling the curse of dimensionality have been developed. These optimization tasks are strongly related to learning problems such as data-driven optimal control and learning of deep neural networks. As a consequence, there is a huge potential to employ control theoretical techniques in Machine Learning. The Mini-Workshop was devoted to discuss possible synergies among the various tools developed in these fields.

Authors 4

1. Giacomo Borghi

   Heriot-Watt University

   Affiliation as printed

   Heriot-Watt University, Edinburgh, UK

2. Elisa Iacomini

   University of Ferrara

   Affiliation as printed

   Università degli Studi di Ferrara, Ferrara, Italy

3. Mathias Oster Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Aachen, Germany

4. Chiara Segala

   Università della Svizzera italiana

   Affiliation as printed

   Università della Svizzera Italiana, Lugano, Switzerland