arXiv Open Access 2023

Quantile and moment neural networks for learning functionals of distributions

Xavier Warin

Lihat Sumber

Abstrak

We study news neural networks to approximate function of distributions in a probability space. Two classes of neural networks based on quantile and moment approximation are proposed to learn these functions and are theoretically supported by universal approximation theorems. By mixing the quantile and moment features in other new networks, we develop schemes that outperform existing networks on numerical test cases involving univariate distributions. For bivariate distributions, the moment neural network outperforms all other networks.

Topik & Kata Kunci

stat.ML cs.LG

Penulis (1)

Xavier Warin

Format Sitasi

APA MLA BibTeX

Warin, X. (2023). Quantile and moment neural networks for learning functionals of distributions. https://arxiv.org/abs/2303.11060

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2023
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓