Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation

Jentzen A, Riekert A (2023)

In: Journal of Mathematical Analysis and Applications, 517(2), 126601.

Research article (journal)

Existence, uniqueness, and convergence rates for gradient flows in the training of artificial neural networks with ReLU activation

Eberle, Simon; Jentzen, Arnulf; Riekert, Adrian; Weiss, Georg S. (2023)

In: Electronic Research Archive, 31(5).

Research article (journal)

A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target functions

Jentzen, Arnulf; Riekert, Adrian (2022)

In: Journal of Machine Learning Research, 23(260).

Research article (journal)

A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions

Cheridito, Patrick; Jentzen, Arnulf; Riekert, Adrian; Rossmannek, Florian (2022)

In: Journal of Complexity, 72, 101646.

Research article (journal)

On the existence of infinitely many realization functions of non-global local minima in the training of artificial neural networks with ReLU activation

Ibragimov, Shokhrukh; Jentzen, Arnulf; Kröger, Timo; Riekert, Adrian (2022)

In: ArXiv:2202.11481.

Research article in digital collection

Publications

Contact

Top-Links

Strong overall error analysis for the training of artificial neural networks via random initializations Jentzen A, Riekert A (2023) In: Communications in Mathematics and Statistics, 0. Research article (journal)
Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation Jentzen A, Riekert A (2023) In: Journal of Mathematical Analysis and Applications, 517(2), 126601. Research article (journal)
Algorithmically Designed Artificial Neural Networks (ADANNs): Higher order deep operator learning for parametric partial differential equations Jentzen, A.; Riekert, A.; von Wurstemberger, P. (2023) In: arXiv.org:2302.03286. Research article in digital collection
Existence, uniqueness, and convergence rates for gradient flows in the training of artificial neural networks with ReLU activation Eberle, Simon; Jentzen, Arnulf; Riekert, Adrian; Weiss, Georg S. (2023) In: Electronic Research Archive, 31(5). Research article (journal)
On the existence of global minima and convergence analyses for gradient descent methods in the training of deep neural networks Jentzen A, Riekert A (2022) In: Journal of Machine Learning, 1(2). Research article (journal)
A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target functions Jentzen, Arnulf; Riekert, Adrian (2022) In: Journal of Machine Learning Research, 23(260). Research article (journal)
A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions Jentzen, Arnulf; Riekert, Adrian (2022) In: Zeitschrift für Angewandte Mathematik und Physik, 73(5), 188. Research article (journal)
A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions Cheridito, Patrick; Jentzen, Arnulf; Riekert, Adrian; Rossmannek, Florian (2022) In: Journal of Complexity, 72, 101646. Research article (journal)
Convergence rates for empirical measures of Markov chains in dual and Wasserstein distances Riekert, Adrian (2022) In: Statistics and Probability Letters, 189, 109605. Research article (journal)
On the existence of infinitely many realization functions of non-global local minima in the training of artificial neural networks with ReLU activation Ibragimov, Shokhrukh; Jentzen, Arnulf; Kröger, Timo; Riekert, Adrian (2022) In: ArXiv:2202.11481. Research article in digital collection