Jul 2026
Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width
The findings reveal that depth plays a more critical role than width in the context of analytic function approximation, and establishes upper bounds for the approximation of analytic functions, which possess infinite smoothness, via ReLU networks under the $(N,L)-characterization.
Yanming Lai, De-Feng Sun, Yang Wang
· arXiv.org · 0 citations