2 papers
math.ST2026
Optimal neural network approximation of smooth compositional functions on sets with low intrinsic dimension
Thomas Nagler, Sophie Langer
We study approximation and statistical learning properties of deep ReLU networks under structural assumptions that mitigate the curse of dimensionality. We prove minimax-optimal un…
stat.ME2025
On dimension reduction in conditional dependence models
Thomas Nagler, Gerda Claeskens, Irène Gijbels
Inference of the conditional dependence structure is challenging when many covariates are present. In numerous applications, only a low-dimensional projection of the covariates inf…