English

A Note On Nonlinear Regression Under L2 Loss

Machine Learning 2023-04-03 v1 Numerical Analysis Numerical Analysis Optimization and Control Machine Learning

Abstract

We investigate the nonlinear regression problem under L2 loss (square loss) functions. Traditional nonlinear regression models often result in non-convex optimization problems with respect to the parameter set. We show that a convex nonlinear regression model exists for the traditional least squares problem, which can be a promising towards designing more complex systems with easier to train models.

Keywords

Cite

@article{arxiv.2303.17745,
  title  = {A Note On Nonlinear Regression Under L2 Loss},
  author = {Kaan Gokcesu and Hakan Gokcesu},
  journal= {arXiv preprint arXiv:2303.17745},
  year   = {2023}
}
R2 v1 2026-06-28T09:42:18.023Z