Mathematik und Informatik
© FB 10

Prof. Dr. Steffen Dereich, Institut für Mathematische Stochastik

Investigator in Mathematics Münster
Field of expertise: Theory of stochastic processes

Private Homepagehttp://www.uni-muenster.de/Stochastik/dereich/
Research InterestsProbability Theory
Topics in
Mathematics Münster


T8: Random discrete structures and their limits
T10: Deep learning and surrogate methods
Current PublicationsDereich, S.; Jentzen, A.; Kassing, S. On the existence of minimizers in shallow residual ReLU neural network optimization landscapes. , 2023 online
Dereich, Steffen; Kassing, Sebastian Central limit theorems for stochastic gradient descent with averaging for stable manifolds*. Electronic Journal of Probability Vol. 28, 2023 online
Dereich, Steffen; Kassing, Sebastian Cooling down stochastic differential equations: Almost sure convergence. Stochastic Processes and their Applications Vol. 152, 2022 online
Dereich, Steffen; Kassing, Sebastian On minimal representations of shallow ReLU networks. Neural Networks Vol. 148, 2022 online
Dereich, Steffen General multilevel adaptations for stochastic approximation algorithms II: CLTs. Stochastic Processes and their Applications Vol. 132, 2021 online
Dereich, Steffen; Mueller-Gronbach, Thomas General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type. Numerische Mathematik Vol. 142 (2), 2019 online
Dereich, Steffen; Ortgiese, Marcel Local Neighbourhoods for First-Passage Percolation on the Configuration Model. Journal of Statistical Physics Vol. 173 (3-4), 2018 online
Betz, Volker; Dereich, Steffen; Moerters, Peter The Shape of the Emerging Condensate in Effective Models of Condensation. Annales Henri Poincare Vol. 19 (6), 2018 online
Current ProjectsEXC 2044 - T08: Random discrete structures and their limits Discrete structures are omnipresent in mathematics, computer science, statistical physics, optimisation and models of natural phenomena. For instance, complex random graphs serve as a model for social networks or the world wide web. Such structures can be descriptions of objects that are intrinsically discrete or they occur as an approximation of continuous objects. An intriguing feature of random discrete structures is that the models exhibit complex macroscopic behaviour, phase transitions in a wide sense, making the field a rich source of challenging mathematical questions. In this topic we will concentrate on three strands of random discrete structures that combine various research interests and expertise present in Münster. online
EXC 2044 - T10: Deep learning and surrogate methods In this topic we will advance the fundamental mathematical understanding of artificial neural networks, e.g., through the design and rigorous analysis of stochastic gradient descent methods for their training. Combining data-driven machine learning approaches with model order reduction methods, we will develop fully certified multi-fidelity modelling frameworks for parameterised PDEs, design and study higher-order deep learning-based approximation schemes for parametric SPDEs and construct cost-optimal multi-fidelity surrogate methods for PDE-constrained optimisation and inverse problems. online
GRK 3027: Rigorous Analysis of Complex Random Systems

The Research Training Group is dedicated to educating mathematicians in the field of complex random systems. It provides a strong platform for the development of both industrial and academic careers for its graduate students. The central theme is a mathematically rigorous understanding of how probabilistic systems, modelled on a microscopic level, behave effectively at a macroscopic scale. A quintessential example for this RTG lies in statistical mechanics, where systems comprising an astronomical number of particles, upwards of 10^{23}, can be accurately described by a handful of observables including temperature and entropy. Other examples come from stochastic homogenisation in material sciences, from the behaviour of training algorithms in machine learning, and from geometric discrete structures build from point processes or random graphs. The challenge to understand these phenomena with mathematical rigour has been and continues to be a source of exciting research in probability theory. Within this RTG we strive for macroscopic representations of such complex random systems. It is the main research focus of this RTG to advance (tools for) both qualitative and quantitative analyses of random complex systems using macroscopic/effective variables and to unveil deeper insights into the nature of these intricate mathematical constructs. We will employ a blend of tools from discrete to continuous probability including point processes, large deviations, stochastic analysis and stochastic approximation arguments. Importantly, the techniques that we will use and the underlying mathematical ideas are universal across projects coming from completely different origin. This particular facet stands as a cornerstone within the RTG, holding significant importance for the participating students. For our students to be able to exploit the synergies between the different projects, they will pass through a structured and rich qualification programme with several specialised courses, regular colloquia and seminars, working groups, and yearly retreats. Moreover, the PhD students will benefit from the lively mathematical community in Münster with a mentoring programme and several interaction and networking activities with other mathematicians and the local industry.

online
E-Mailsteffen dot dereich at uni-muenster dot de
Phone+49 251 83-32671
FAX+49 251 83-32712
Room130.008
Secretary   Sekretariat Stochastik
Frau Claudia Giesbert
Telefon +49 251 83-33792
Fax +49 251 83-32712
Zimmer 120.002
AddressProf. Dr. Steffen Dereich
Institut für Mathematische Stochastik
Fachbereich Mathematik und Informatik der Universität Münster
Orléans-Ring 10
48149 Münster
Diese Seite editieren