English

Tukey g-and-h neural network regression for non-Gaussian data

Machine Learning 2024-11-13 v1 Machine Learning

Abstract

This paper addresses non-Gaussian regression with neural networks via the use of the Tukey g-and-h distribution.The Tukey g-and-h transform is a flexible parametric transform with two parameters gg and hh which, when applied to a standard normal random variable, introduces both skewness and kurtosis, resulting in a distribution commonly called the Tukey g-and-h distribution. Specific values of gg and hh produce good approximations to other families of distributions, such as the Cauchy and student-t distributions. The flexibility of the Tukey g-and-h distribution has driven its popularity in the statistical community, in applied sciences and finance. In this work we consider the training of a neural network to predict the parameters of a Tukey g-and-h distribution in a regression framework via the minimization of the corresponding negative log-likelihood, despite the latter having no closed-form expression. We demonstrate the efficiency of our procedure in simulated examples and apply our method to a real-world dataset of global crop yield for several types of crops. Finally, we show how we can carry out a goodness-of-fit analysis between the predicted distributions and the test data. A Pytorch implementation is made available on Github and as a Pypi package.

Keywords

Cite

@article{arxiv.2411.07957,
  title  = {Tukey g-and-h neural network regression for non-Gaussian data},
  author = {Arthur P. Guillaumin and Natalia Efremova},
  journal= {arXiv preprint arXiv:2411.07957},
  year   = {2024}
}
R2 v1 2026-06-28T19:57:21.219Z