collaborators
Showing math.OCShow all

8 papers · 1 filter

math.OC2026

On MUON optimization: From non-convergence to an error analysis with Polar Express and the Newton-Schulz polynomial from implementations

Thang Do, Steffen Dereich, Arnulf Jentzen

Stochastic gradient descent (SGD) optimization methods are the standard instruments for the training of deep neural networks (DNNs). In many relevant artificial intelligence (AI) s…

math.OC2026

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

The standard stochastic gradient descent (SGD) optimization method, as well as adaptive methods such as the Adam optimizer fail to converge if the learning rates do not converge to…

math.OC2026

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

Steffen Dereich, Thang Do, Arnulf Jentzen +1

Beside the standard stochastic gradient descent (SGD) method, the Adam optimizer due to Kingma & Ba (2014) is currently probably the best-known optimization method for the training…

math.OC2025

ODE approximation for the Adam algorithm: General and overparametrized setting

Steffen Dereich, Arnulf Jentzen, Sebastian Kassing

The Adam optimizer is currently presumably the most popular optimization method in deep learning. In this article we develop an ODE based method to study the Adam optimizer in a fa…

math.OC2025

Asymptotic stability properties and a priori bounds for Adam and other gradient descent optimization methods

Steffen Dereich, Robin Graeber, Arnulf Jentzen +1

Gradient descent (GD) based optimization methods are these days the standard tools to train deep neural networks in artificial intelligence systems. In optimization procedures in d…

math.OC2025

Sharp higher order convergence rates for the Adam optimizer

Steffen Dereich, Arnulf Jentzen, Adrian Riekert

Gradient descent based optimization methods are the methods of choice to train deep neural networks in machine learning. Beyond the standard gradient descent method, also suitable…