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...

Cijeli opis

Bibliografski detalji

Glavni autori:	Ibrahim Elsharkawy, Benjamin Hooberman, Yonatan Kahn
Format:	Artigo
Jezik:	Inglês
Izdano:	IOP Publishing 2025-01-01
Serija:	Machine Learning: Science and Technology
Teme:	uncertainty quantification neural network ensemble neural tangent kernel infinite-width limit scaling laws
Online pristup:	https://doi.org/10.1088/2632-2153/adf7fe
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!