Dennis Elbrächter

Postdoc, Universität Vienna

Joined

July 2019

Names

Dennis Elbrächter

Emails

****@univie.ac.at (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

Postdoc

Universität Vienna (univie.ac.at)

2025 – Present

Postdoc

University of Genoa (unige.it)

2024 – 2025

Postdoc

ETHZ - ETH Zurich (ethz.ch)

2021 – 2023

PhD student

Universität Vienna (univie.ac.at)

2017 – 2021

Advisors, Relations & Conflicts

PhD Advisor

Philipp Grohs

Present

Postdoc Advisor

Helmut Bölcskei

Present

Postdoc Advisor

Philipp Christian Petersen

Present

Expertise

approximation theory

neural networks

Present

Publications

MAD: Manifold Attracted Diffusion
Dennis Elbrächter, Giovanni S Alberti, Matteo Santacesaria
- Submitted to ICLR 2026
- Readers: Everyone
MAD: Manifold Attracted Diffusion
Dennis Elbrächter, Giovanni S. Alberti, Matteo Santacesaria
- CoRR 2025
- Readers: Everyone
Redistributor: Transforming Empirical Data Distributions
Pavol Harár, Dennis Elbrächter, Monika Dörfler, Kory D. Johnson
- CoRR 2022
- Readers: Everyone
Deep Neural Network Approximation Theory
Dennis Elbrächter, Dmytro Perekrestenko, Philipp Grohs, Helmut Bölcskei
- IEEE Trans. Inf. Theory 2021
- Readers: Everyone
Deep Neural Network Approximation Theory
Philipp Grohs, Dmytro Perekrestenko, Dennis Elbrächter, Helmut Bölcskei
- CoRR 2019
- Readers: Everyone
How degenerate is the parametrization of neural networks with the ReLU activation function?
Julius Berner, Dennis Elbrächter, Philipp Grohs
- CoRR 2019
- Readers: Everyone
The Oracle of DLphi
Dominik Alfke, Weston Baines, Jan Blechschmidt, Mauricio J. del Razo Sarmina, Amnon Drory, Dennis Elbrächter, Nando Farchmin, Matteo Gambara, Silke Glas, Philipp Grohs, Peter Hinz, Danijel Kivaranovic, Christian Kümmerle, Gitta Kutyniok, Sebastian Lunz, Jan MacDonald, Ryan Malthaner, Gregory Naisat, Ariel Neufeld, Philipp Christian Petersen et al. (7 additional authors not shown)
- 2019 (modified: 28 Jan 2026)
- CoRR 2019
- Readers: Everyone
How degenerate is the parametrization of neural networks with the ReLU activation function?
Dennis Elbrächter, Julius Berner, Philipp Grohs
- 2019 (modified: 28 Jan 2026)
- NeurIPS 2019
- Readers: Everyone
Towards a regularity theory for ReLU networks - chain rule and global error estimates
Julius Berner, Dennis Elbrächter, Philipp Grohs, Arnulf Jentzen
- 2019 (modified: 28 Jan 2026)
- CoRR 2019
- Readers: Everyone
The universal approximation power of finite-width deep ReLU networks
Dmytro Perekrestenko, Philipp Grohs, Dennis Elbrächter, Helmut Bölcskei
- CoRR 2018
- Readers: Everyone

Co-Authors

View all 36 co-authors