Saved in:
Bibliographic Details
Main Author: Ruggieri, Giovanni
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.00101
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918076663988224
author Ruggieri, Giovanni
author_facet Ruggieri, Giovanni
contents We introduce DFReg, a physics-inspired regularization method for deep neural networks that operates on the global distribution of weights. Drawing from Density Functional Theory (DFT), DFReg applies a functional penalty to encourage smooth, diverse, and well-distributed weight configurations. Unlike traditional techniques such as Dropout or L2 decay, DFReg imposes global structural regularity without architectural changes or stochastic perturbations.
format Preprint
id arxiv_https___arxiv_org_abs_2507_00101
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DFReg: A Physics-Inspired Framework for Global Weight Distribution Regularization in Neural Networks
Ruggieri, Giovanni
Machine Learning
We introduce DFReg, a physics-inspired regularization method for deep neural networks that operates on the global distribution of weights. Drawing from Density Functional Theory (DFT), DFReg applies a functional penalty to encourage smooth, diverse, and well-distributed weight configurations. Unlike traditional techniques such as Dropout or L2 decay, DFReg imposes global structural regularity without architectural changes or stochastic perturbations.
title DFReg: A Physics-Inspired Framework for Global Weight Distribution Regularization in Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2507.00101