Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
High-dimensional classification problems with Barron regular boundaries under margin conditions
Jonathan GarcÃa, Philipp Petersen
We prove that a classifier with a Barron-regular decision boundary can be approximated with a rate of high polynomial degree by ReLU neural networks with three hidden layers when a…
cs.LG2024
Dimension-independent learning rates for high-dimensional classification problems
Andres Felipe Lerma-Pineda, Philipp Petersen, Simon Frieder +1
We study the problem of approximating and estimating classification functions that have their decision boundary in the space. Functions of type arise naturally as s…