The GroupMax neural network approximation of convex functions
From MaRDI portal
Publication:6402003
arXiv2206.06622MaRDI QIDQ6402003FDOQ6402003
Publication date: 14 June 2022
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.
This page was built for publication: The GroupMax neural network approximation of convex functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6402003)
