Steffen Dereich

According to our database, Steffen Dereich authored at least 24 papers between 2003 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Uniform a priori bounds and error analysis for the Adam stochastic gradient descent optimization method.

Steffen Dereich, Thang Do, Arnulf Jentzen

CoRR, March, 2026

2025

Adam symmetry theorem: characterization of the convergence of the stochastic Adam optimizer.

Steffen Dereich, Thang Do, Arnulf Jentzen, Philippe von Wurstemberger

CoRR, November, 2025

ODE approximation for the Adam algorithm: General and overparametrized setting.

Steffen Dereich, Arnulf Jentzen, Sebastian Kassing

CoRR, November, 2025

SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures.

Julian Kranz, Davide Gallon, Steffen Dereich, Arnulf Jentzen

CoRR, May, 2025

Sharp higher order convergence rates for the Adam optimizer.

Steffen Dereich, Arnulf Jentzen, Adrian Riekert

CoRR, April, 2025

In almost all shallow analytic neural network optimization landscapes, efficient minimizers have strongly convex neighborhoods.

Felix Benning, Steffen Dereich

CoRR, April, 2025

Mathematical analysis of the gradients in deep learning.

Steffen Dereich, Thang Do, Arnulf Jentzen, Frederic Weber

CoRR, January, 2025

Averaged Adam accelerates stochastic optimization in the training of deep neural network approximations for partial differential equation and optimal control problems.

Steffen Dereich, Arnulf Jentzen, Adrian Riekert

CoRR, January, 2025

2024

On the Existence of Minimizers in Shallow Residual ReLU Neural Network Optimization Landscapes.

Steffen Dereich, Arnulf Jentzen, Sebastian Kassing

SIAM J. Numer. Anal., 2024

Convergence rates for the Adam optimizer.

Steffen Dereich, Arnulf Jentzen

CoRR, 2024

Non-convergence of Adam and other adaptive stochastic gradient descent optimization methods for non-vanishing learning rates.

Steffen Dereich, Robin Graeber, Arnulf Jentzen

CoRR, 2024

Learning rate adaptive stochastic gradient descent optimization methods: numerical simulations for deep learning methods for partial differential equations and convergence analyses.

Steffen Dereich, Arnulf Jentzen, Adrian Riekert

CoRR, 2024

2023

On the existence of optimal shallow feedforward networks with ReLU activation.

Steffen Dereich, Sebastian Kassing

CoRR, 2023

2022

On minimal representations of shallow ReLU networks.

Steffen Dereich, Sebastian Kassing

Neural Networks, 2022

2021

Convergence of stochastic gradient descent schemes for Lojasiewicz-landscapes.

Steffen Dereich, Sebastian Kassing

CoRR, 2021

2019

General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type.

Steffen Dereich, Thomas Müller-Gronbach

Numerische Mathematik, 2019

2015

Cycle length distributions in random permutations with diverging cycle weights.

Steffen Dereich, Peter Mörters

Random Struct. Algorithms, 2015

Quadrature for Self-affine Distributions on R^d.

Steffen Dereich, Thomas Müller-Gronbach

Found. Comput. Math., 2015

2014

Robust Analysis of Preferential Attachment Models with Fitness.

Steffen Dereich, Marcel Ortgiese

Comb. Probab. Comput., 2014

Multilevel Monte Carlo Implementation for SDEs Driven by Truncated Stable Processes.

Steffen Dereich, Sangmeng Li

Proceedings of the Monte Carlo and Quasi-Monte Carlo Methods, 2014

2009

High resolution quantization and entropy coding of jump processes.

Frank Aurzada, Steffen Dereich, Michael Scheutzow, Christian Vormoor

J. Complex., 2009

Infinite-Dimensional Quadrature and Approximation of Distributions.

Jakob Creutzig, Steffen Dereich, Thomas Müller-Gronbach, Klaus Ritter

Found. Comput. Math., 2009

The Coding Complexity of Lévy Processes.

Frank Aurzada, Steffen Dereich

Found. Comput. Math., 2009

2003

High resolution coding of stochastic processes and small ball probabilities.

Steffen Dereich

PhD thesis, 2003