English

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.

Keywords

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

R2 v1 2026-06-24T11:50:19.261Z