Uncertainty quantification from ensemble variance scaling laws in deep neural networks

Quantifying the uncertainty from machine learning analyses is critical to their use in the physical sciences. In this work we focus on uncertainty inherited from the initialization distribution of neural networks. We compute the mean $\mu_{\mathcal{L}}$ and variance $\sigma_{\mathcal{L}}^2$ of the t...

Full description

Bibliographic Details

Published in:	Machine Learning: Science and Technology
Main Authors:	Ibrahim Elsharkawy, Benjamin Hooberman, Yonatan Kahn
Format:	Article
Language:	English
Published:	IOP Publishing 2025-01-01
Subjects:	uncertainty quantification neural network ensemble neural tangent kernel infinite-width limit scaling laws
Online Access:	https://doi.org/10.1088/2632-2153/adf7fe