Diyora Salimova
ETH Zurich
Address:
Diyora Salimova
Chair for Mathematical Information Science
Department of Information Technology and Electrical Engineering
ETH Zurich
Sternwartstrasse 7
8092 Zürich
Switzerland
Office: Room E 117
Phone: +41 44 632 26 04
Email: sdiyora (add "@mins.ee.ethz.ch")
Links:
[Profile on ResearchGate]
[Profile on GoogleScholar]
[Profile on MathSciNet]
[Homepage at ETHZ]
Research interests
 approximation properties of deep neural networks, mathematics for deep learning, machine learning, stochastic gradient descent methods, computational stochastics/stochastic numerics, stochastic differential equations, stochastic analysis, numerical analysis, learning dynamical systems
Positions
Education
 09/201612/2019: Doctor of Sciences of ETH Zurich, Switzerland. PhD supervisor: Prof. Dr. Arnulf Jentzen
 09/201310/2015: Master of Science in Applied Mathematics, ETH Zurich, Switzerland
 09/201106/2013: Bachelor of Science in Mathematics, Jacobs University Bremen, Germany
 09/200906/2011: Completed two years of study in undergraduate Mathematics, Samarkand State University, Uzbekistan
Preprints
(authors listed in alphabetical order)
 Bercher, A., Gonon, L., Jentzen, A., and Salimova, D.,
Weak error analysis for stochastic gradient descent optimization algorithms.
[arXiv] (2020), 123 pages.
 Hornung, F., Jentzen, A., and Salimova, D.,
Spacetime deep neural network approximations for highdimensional partial differential equations.
[arXiv] (2020), 52 pages.
 Grohs, P., Jentzen, A., and Salimova, D.,
Deep neural network approximations for Monte Carlo algorithms.
[arXiv] (2019), 45 pages. Revision requested from Springer Nat. Part. Diff. Equ. Appl.
 Beccari, M., Hutzenthaler, M., Jentzen, A., Kurniawan, R., Lindner, F., and Salimova, D.,
Strong and weak divergence of exponential and linearimplicit Euler approximations for stochastic partial differential equations with superlinearly growing nonlinearities.
[arXiv] (2019), 65 pages.
 Jentzen, A., Mazzonetto, S., and Salimova, D.,
Existence and uniqueness properties for solutions of a class of Banach space valued evolution equations.
[arXiv] (2018), 28 pages.
 Jentzen, A., Salimova, D., and Welti, T.,
A proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients.
[arXiv] (2018), 48 pages. Revision requested from Comm. Math. Sci.
Published papers
(authors listed in alphabetical order)
 Mazzonetto, S., and Salimova, D.,
Existence, uniqueness, and numerical approximations for stochastic Burgers equations.
Stoch. Anal. Appl. 38 (2020), no. 4, 623646.
[arXiv].
 Jentzen, A., Salimova, D., and Welti, T.,
Strong convergence for explicit spacetime discrete numerical approximation methods for stochastic Burgers equations.
J. Math. Anal. Appl. 469 (2019), no. 2, 661704.
[arXiv].
 Hutzenthaler, M., Jentzen, A., and Salimova, D.,
Strong convergence of fulldiscrete nonlinearitytruncated accelerated exponential Eulertype approximations for stochastic KuramotoSivashinsky equations.
Comm. Math. Sci. 16 (2018), no. 6, 14891529.
[arXiv].
 Gerencsér, M., Jentzen, A., and Salimova, D.,
On stochastic differential equations with arbitrarily slow convergence rates for strong approximation in two space dimensions.
Proc. Roy. Soc. London A 473 (2017).
[arXiv].
 Ibragimov, Z. and Salimova, D.,
On an inequality in l_p(C) involving Basel problem.
Elem. Math. 70 (2015), 7981.
Teaching
