13 citations · 15 across the 2 of their papers we have counts for
2 papers
math.ST2020★ 2 cited
Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation
Arnulf Jentzen, Timo Welti
In spite of the accomplishments of deep learning based algorithms in numerous applications and very broad corresponding research interest, at the moment there is still no rigorous…
math.NA2019★ 13 cited
Generalised multilevel Picard approximations
Michael B. Giles, Arnulf Jentzen, Timo Welti
It is one of the most challenging problems in applied mathematics to approximatively solve high-dimensional partial differential equations (PDEs). In particular, most of the numeri…