The GroupMax neural network approximation of convex functions
Optimization and Control
2023-01-27 v2
Abstract
We present a new neural network to approximate convex functions. This network has the particularity to approximate the function with cuts and can be easily adapted to partial convexity. We give an universal approximation theorem in the full convex case and give many numerical results proving it efficiency.
Cite
@article{arxiv.2206.06622,
title = {The GroupMax neural network approximation of convex functions},
author = {Xavier Warin},
journal= {arXiv preprint arXiv:2206.06622},
year = {2023}
}
Comments
10 pages 16 figures