3 papers
cs.LG2026
High Probability Derivative Bounds for Random tanh Neural Networks on a Hypercube
Josef Dick, Michael Feischl, Fabian Zehetgruber
We establish high-probability bounds for mixed input derivatives of wide random neural networks whose activation derivatives satisfy a factorial growth bound. Our main result speci…
math.NA2025
Computational Math with Neural Networks is Hard
Michael Feischl, Fabian Zehetgruber, Benedikt Grässle
We establish asymptotic complexity barriers for three basic numerical tasks with neural-network data: integration of a network realization, solution of a Poisson problem with a neu…
math.NA2024
Towards optimal hierarchical training of neural networks
Michael Feischl, Alexander Rieder, Fabian Zehetgruber
We propose a hierarchical training algorithm for standard feed-forward neural networks that adaptively extends the network architecture as soon as the optimization reaches a statio…