2 papers
cs.LG2026
Limitations of Learning Tanh Neural Networks with Finite Precision
Philipp Grohs, Matěj Trödler
We investigate limitations of learning neural networks from point evaluations under finite-precision computations and accuracy guarantees, building on Berner, Grohs,…
math.CO2025
Lower bounds on the minimal dispersion of point sets via cover-free families
Matěj Trödler, Jan Volec, Jan Vybíral
We elaborate on the intimate connection between the largest volume of an empty axis-parallel box in a set of points from and cover-free families from the extremal set…