Skip to content
Technical University of Munich

Dr. Nadiia Derevianko

Position

  • Researcher in Physics-enhanced Machine Learning at Technical University of Munich, Germany

Address

Technical University of Munich
TUM School of CIT
Department of Computer Science
Boltzmannstraße 3
85748 Garching
Germany

Office: MI 02.05.040
Email: nadiia.derevianko@tum.de
Office hours: by arrangement

Teaching

WiSe 2025/2026

  • Lecture: Einführung in die wissenschaftliche Programmierung (Monday 10:00-12:00, 4 SWS (2V + 2Ü) / 5 Credits, German)

SoSe 2025

  • Lecture: Algorithms for Scientific Computing (Monday 14:00-16:00, Wednesday 08:00-10:00, 6 SWS (4V + 2Ü) / 8 Credits, English)

Supervision: Student Projects

Ongoing Projects: 

  • Ngoc Kim Ngan Nguyen (Bachelor's Thesis): Solving partial differential equations by sampled neural networks with adaptive activation functions
  • Awar Satar (Bachelor's Thesis): Application of the non-uniform neural operator in NVIDIA PhysicsNeMo
  • Nikolas Anton Lethaus (Master's Thesis): Minimal pole-residue representation and analytic continuation of correlation functions
  • David Wachtler (IDP): Rational function-based approach for approximation of graph convolution operator
  • Franziska Wagner (Bachelor's Thesis): Classification of EEG motor movement/imagery signals using rational Discrete Short-Time Fourier Transform

Finished Projects:

  • Yichen Tang (Master's Thesis): Neural networks with adaptive activation functions and their application to the solution of PDEs, August 2025
  • Abdul Ikhlaq (Master's Thesis): Fast algorithm for Protein-Ligand Docking, September 2025

 

Recent preprints and publications

Publications:

  • Nadiia Derevianko, Recovery of rational functions via Hankel pencil method and sensitivities of the poles, to appear in Anal. Appl. https://arxiv.org/abs/2406.13192 

Preprints:

  • Nadiia Derevianko, Ioannis G. Kevrekidis, Felix Dietrich, Neural network-based singularity detection and applications, Arxiv preprint: arxiv.org/abs/2509.10110
  • Nadiia Derevianko, Gerlind Plonka, Differential approximation of the Gaussian by short cosine sums with exponential error decay, Arxiv preprint: https://arxiv.org/abs/2307.13587 (revised)
  • Nadiia Derevianko, Lennart Hübner, Parameter estimation for multivariate exponential sums via iterative rational approximation, Arxiv preprint: arxiv.org/abs/2504.19157

See www.researchgate.net/profile/Nadiia-Derevianko

To top