activity
20042024
most citedMultilevel Monte Carlo algorithms for Lévy-driven SDEs with Gaussian correction

98 citations · 308 across the 30 of their papers we have counts for

collaborators

34 papers

math.PR2024

Traces left by random walks on large random graphs: local limits

Steffen Dereich

In this article, we develop a theory for understanding the traces left by a random walk in the vicinity of a randomly chosen reference vertex. The analysis is related to interlacem…

cs.LG2023★ 5 cited

On the existence of optimal shallow feedforward networks with ReLU activation

Steffen Dereich, Sebastian Kassing

We prove existence of global minima in the loss landscape for the approximation of continuous target functions using shallow feedforward artificial neural networks with ReLU activa…

math.OC2023★ 1 cited

On the existence of minimizers in shallow residual ReLU neural network optimization landscapes

Steffen Dereich, Arnulf Jentzen, Sebastian Kassing

In this article, we show existence of minimizers in the loss landscape for residual artificial neural networks (ANNs) with multi-dimensional input layer and one hidden layer with R…

cs.LG2021★ 1 cited

On minimal representations of shallow ReLU networks

S. Dereich, S. Kassing

The realization function of a shallow ReLU network is a continuous and piecewise affine function , where the domain is partitioned by a…

math.PR2021

Quasi-processes for branching Markov chains

Steffen Dereich, Martin Maiwald

Potential theory is a central tool to understand and analyse Markov processes. In this article, we develop its probabilistic counterpart for branching Markov chains. Specifically,…

math.PR2021★ 9 cited

Cooling down stochastic differential equations: almost sure convergence

S. Dereich, S. Kassing

We consider almost sure convergence of the SDE under the existence of a -Lyapunov function . More explicitly, we show t…