Steffen Dereich

26 papers Journal 24Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
Uniform a priori bounds and error analysis for the Adam stochastic gradient descent optimization method.
CoRR
Steffen Dereich, Thang Do, Arnulf Jentzen
2025 J jnl
Adam symmetry theorem: characterization of the convergence of the stochastic Adam optimizer.
CoRR
Steffen Dereich, Thang Do, Arnulf Jentzen, Philippe von Wurstemberger
2025 J jnl
Averaged Adam accelerates stochastic optimization in the training of deep neural network approximations for partial differential equation and optimal control problems.
CoRR
Steffen Dereich, Arnulf Jentzen, Adrian Riekert
2025 J jnl
In almost all shallow analytic neural network optimization landscapes, efficient minimizers have strongly convex neighborhoods.
CoRR
Felix Benning, Steffen Dereich
2025 J jnl
Mathematical analysis of the gradients in deep learning.
CoRR
Steffen Dereich, Thang Do, Arnulf Jentzen, Frederic Weber
2025 J jnl
ODE approximation for the Adam algorithm: General and overparametrized setting.
CoRR
Steffen Dereich, Arnulf Jentzen, Sebastian Kassing
2025 J jnl
SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures.
CoRR
Julian Kranz, Davide Gallon, Steffen Dereich, Arnulf Jentzen
2025 J jnl
Sharp higher order convergence rates for the Adam optimizer.
CoRR
Steffen Dereich, Arnulf Jentzen, Adrian Riekert
2024 J jnl
Convergence rates for the Adam optimizer.
CoRR
Steffen Dereich, Arnulf Jentzen
2024 J jnl
Learning rate adaptive stochastic gradient descent optimization methods: numerical simulations for deep learning methods for partial differential equations and convergence analyses.
CoRR
Steffen Dereich, Arnulf Jentzen, Adrian Riekert
2024 J jnl
Non-convergence of Adam and other adaptive stochastic gradient descent optimization methods for non-vanishing learning rates.
CoRR
Steffen Dereich, Robin Graeber, Arnulf Jentzen
2024 J jnl
On the Existence of Minimizers in Shallow Residual ReLU Neural Network Optimization Landscapes.
SIAM J. Numer. Anal.
Steffen Dereich, Arnulf Jentzen, Sebastian Kassing
2023 J jnl
On the existence of minimizers in shallow residual ReLU neural network optimization landscapes.
CoRR
Steffen Dereich, Arnulf Jentzen, Sebastian Kassing
2023 J jnl
On the existence of optimal shallow feedforward networks with ReLU activation.
CoRR
Steffen Dereich, Sebastian Kassing
2022 J jnl
On minimal representations of shallow ReLU networks.
Neural Networks
Steffen Dereich, Sebastian Kassing
2021 J jnl
Convergence of stochastic gradient descent schemes for Lojasiewicz-landscapes.
CoRR
Steffen Dereich, Sebastian Kassing
2021 J jnl
On minimal representations of shallow ReLU networks.
CoRR
Steffen Dereich, Sebastian Kassing
2019 J jnl
General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type.
Numerische Mathematik
Steffen Dereich, Thomas Müller-Gronbach
2015 J jnl
Cycle length distributions in random permutations with diverging cycle weights.
Random Struct. Algorithms
Steffen Dereich, Peter Mörters
2015 J jnl
Quadrature for Self-affine Distributions on R
Found. Comput. Math.
Steffen Dereich, Thomas Müller-Gronbach
2014 — conf
Multilevel Monte Carlo Implementation for SDEs Driven by Truncated Stable Processes.
MCQMC
Steffen Dereich, Sangmeng Li
2014 J jnl
Robust Analysis of Preferential Attachment Models with Fitness.
Comb. Probab. Comput.
Steffen Dereich, Marcel Ortgiese
2009 J jnl
High resolution quantization and entropy coding of jump processes.
J. Complex.
Frank Aurzada, Steffen Dereich, Michael Scheutzow, Christian Vormoor
2009 J jnl
Infinite-Dimensional Quadrature and Approximation of Distributions.
Found. Comput. Math.
Jakob Creutzig, Steffen Dereich, Thomas Müller-Gronbach, Klaus Ritter
2009 J jnl
The Coding Complexity of Lévy Processes.
Found. Comput. Math.
Frank Aurzada, Steffen Dereich
2003 — —
High resolution coding of stochastic processes and small ball probabilities.
Steffen Dereich