Private Homepage https://www.uni-muenster.de/AMM/Jentzen/Mitarbeiter/included.shtml Research Interests Mathematics for machine learningNumerical approximations for high-dimensional partial differential equationsNumerical approximations for stochastic differential equationsDeep Learning Selected Publications •Hairer M, Hutzenthaler M, Jentzen A. Loss of regularity for Kolmogorov equations. Ann. Probab., Vol. 43 (2), 2015, pp 468-527 online •Hutzenthaler M, Jentzen A. On a perturbation theory and on strong convergence rates for stochastic ordinary and partial differential equations with nonglobally monotone coefficients. Ann. Probab., Vol. 48 (1), 2020, pp 53-93 online •Hutzenthaler M, Jentzen A, Kloeden PE. Strong and weak divergence in finite time of Euler's method for stochastic differential equations with non-globally Lipschitz continuous coefficients. Proc. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci., Vol. 467 (2130), 2011, pp 1563-1576 online •Fehrman B, Gess B, Jentzen A. Convergence rates for the stochastic gradient descent method for non-convex objective functions. J. Mach. Learn. Res., Vol. 21, 2020, pp Paper No. 136, 48 •Han J, Jentzen A, E W. Solving high-dimensional partial differential equations using deep learning. Proc. Natl. Acad. Sci. USA, Vol. 115 (34), 2018, pp 8505-8510 online •E W, Han J, Jentzen A. Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations. Commun. Math. Stat., Vol. 5 (4), 2017, pp 349-380 online •Hutzenthaler M, Jentzen A, Kloeden PE. Strong convergence of an explicit numerical method for SDEs with nonglobally Lipschitz continuous coefficients. Ann. Appl. Probab., Vol. 22 (4), 2012, pp 1611-1641 •Hutzenthaler M, Jentzen A. Numerical approximations of stochastic differential equations with non-globally Lipschitz continuous coefficients. Mem. Amer. Math. Soc., Vol. 236 (1112), 2015, pp v+99 online •Hutzenthaler M, Jentzen A, Kruse T, Nguyen TA, von Wurstemberger P. Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations. Proc. A., Vol. 476 (2244), 2020, pp 630-654 online Selected Projects •Mathematische Theorie zu Tiefem Lernen. Das zentrale Ziel dieses Projektes ist es eine rigorose mathematische Analyse fuer tief lernende Algorithmen zu entwickeln und damit mathematische Aussagen zu beweisen, welche sowohl den Erfolg als auch die Limitierungen von tief lernenden Algorithmen erklaeren. Insbesondere beabsichtigen wir in diesem Projekt (i) eine mathematische Theorie zu hochdimensionalen approximationseigenschaften von tiefen neuronalen Netzwerken zu entwickeln, (ii) geeignete glatte Funktionenfolgen, welche ohne den Fluch der Dimension von tiefen jedoch nicht von flachen neuronalen Netzwerken approximiert werden koennen, anzugeben und (iii) dimensionsunabhaengige Konvergenzraten fuer stochastische Gradientenverfahren mit hoechstens polynomiell in der Dimension wachsenden Fehlerkonstanten zu beweisen.. •Ueberwindung des Fluches der Dimension: Stochastische Approximationsalgorithmen fuer hochdimensionale partielle Differentialgleichungen. Partial differential equations (PDEs) are among the most universal tools used in modeling problems in nature and man-made complex systems. The PDEs appearing in applications are often high dimensional. Such PDEs can typically not be solved explicitly and developing efficient numerical algorithms for high dimensional PDEs is one of the most challenging tasks in applied mathematics. As is well-known, the difficulty lies in the so-called ''curse of dimensionality'' in the sense that the computational effort of standard approximation algorithms grows exponentially in the dimension of the considered PDE. It is the key objective of this research project to overcome this curse of dimensionality and to construct and analyze new approximation algorithms which solve high dimensional PDEs with a computational effffort that grows at most polynomially in both the dimension of the PDE and the reciprocal of the prescribed approximation precision.. •Existenz-, Eindeutigkeit- und Regularitaetseigenschaften von Loesungen von partielle Differentialgleichungen. The goal of this project is to reveal existence, uniqueness, and regularity properties of solutions of partial differential equations (PDEs). In particular, we intend to study existence, uniqueness, and regularity properties of viscosity solutions of degenerate semilinear Kolmogorov PDEs of the parabolic type. We plan to investigate such PDEs by means of probabilistic representations of the Feynman-Kac type. We also intend to study the connections of such PDEs to optimal control problems.. •Regularitaetseigeschaften und approximationen fuer stochastische gewoehnliche und partielle Differentialgleichungen mit nicht global Lipschitz-stetigen Nichtlinearitaeten. A number of stochastic ordinary and partial differential equations from the literature (such as, for example, the Heston and the 3/2-model from financial engineering, (overdamped) Langevin-type equations from molecular dynamics, stochastic spatially extended FitzHugh-Nagumo systems from neurobiology, stochastic Navier-Stokes equations, Cahn-Hilliard-Cook equations) contain non-globally Lipschitz continuous nonlinearities in their drift or diffusion coefficients. A central aim of this project is to investigate regularity properties with respect to the initial values of such stochastic differential equations in a systematic way. A further goal of this project is to analyze the regularity of solutions of the deterministic Kolmogorov partial dfferential equations associated to such stochastic differential equations. Another aim of this project is to analyze weak and strong convergence and convergence rates of numerical approximations for such stochastic differential equations.. Project membershipMathematics Münster C: Models and ApproximationsC1: Evolution and asymptoticsC4: Geometry-based modelling, approximation, and reduction Current Publications • Cheridito P, Jentzen A, Riekert A, Rossmannek F A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions. J. Complexity Vol. 0, 2022 online• E W, Han J, Jentzen A Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning. Nonlinearity Vol. 35 (1), 2022, pp 278-310 online• Grohs P, Ibragimov S, Jentzen A, Koppensteiner S Lower bounds for artificial neural network approximations: A proof that shallow neural networks fail to overcome the curse of dimensionality. J. Complexity Vol. 0, 2021 online• Hutzenthaler M, Jentzen A, Kuckuck B, Padgett JL Strong $L^p$-error analysis of nonlinear Monte Carlo approximations for high-dimensional semilinear partial differential equations. arXiv Vol. 0, 2021 online• Jentzen A, Riekert A Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation. arXiv Vol. 0, 2021 online• Jentzen A, Kröger T Convergence rates for gradient descent in the training of overparameterized artificial neural networks with biases. arXiv Vol. 0, 2021 online• Cox S, Hutzenthaler M, Jentzen A Local Lipschitz continuity in the initial value and strong completeness for nonlinear stochastic differential equations. Mem. Amer. Math. Soc. Vol. 0, 2021 online• Beck C, Hutzenthaler M, Jentzen A, Magnani E Full history recursive multilevel Picard approximations for ordinary differential equations with expectations. arXiv Vol. 0, 2021 online• Jentzen A, Riekert A On the existence of global minima and convergence analyses for gradient descent methods in the training of deep neural networks. arXiv Vol. 0, 2021 online Current Projects • Dynamical systems and irregular gradient flows online• Mathematical Theory for Deep Learning online• Existence, uniqueness, and regularity properties of solutions of partial differential equations online• Regularity properties and approximations for stochastic ordinary and partial differential equations with non-globally Lipschitz continuous nonlinearities online• Overcoming the curse of dimensionality: stochastic algorithms for high-dimensional partial differential equations online• EXC 2044 - C1: Evolution and asymptotics online• EXC 2044 - C3: Interacting particle systems and phase transitions online E-Mail ajentzen@uni-muenster.de Phone +49 251 83-33793 FAX +49 251 83-32729 Room 120.005 Secretary Sekretariat Claudia GiesbertFrau Claudia GiesbertTelefon +49 251 83-33792Fax +49 251 83-32729Zimmer 120.002 Address Prof. Dr. Arnulf Jentzen Angewandte Mathematik Münster: Institut für Analysis und NumerikFachbereich Mathematik und Informatik der Universität MünsterOrléans-Ring 1048149 Münster Diese Seite editieren