Saved in:
Bibliographic Details
Main Author: Terin, Rodrigo Carmo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.14729
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908836640587776
author Terin, Rodrigo Carmo
author_facet Terin, Rodrigo Carmo
contents Neural networks with positively homogeneous activations exhibit an exact continuous reparametrization symmetry: neuron-wise rescalings generate parameter-space orbits along which the input--output function is invariant. We interpret this symmetry as a gauge redundancy and introduce gauge-adapted coordinates that separate invariant and scale-imbalance directions. Inspired by gauge fixing in field theory, we introduce a soft orbit-selection (norm-balancing) functional acting only on redundant scale coordinates. We show analytically that it induces dissipative relaxation of imbalance modes to preserve the realized function. In controlled experiments, this orbit-selection penalty expands the stable learning-rate regime and suppresses scale drift without changing expressivity. These results establish a structural link between gauge-orbit geometry and optimization conditioning, providing a concrete connection between gauge-theoretic concepts and machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2602_14729
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Scale redundancy and soft gauge fixing in positively homogeneous neural networks
Terin, Rodrigo Carmo
Machine Learning
Artificial Intelligence
Neural networks with positively homogeneous activations exhibit an exact continuous reparametrization symmetry: neuron-wise rescalings generate parameter-space orbits along which the input--output function is invariant. We interpret this symmetry as a gauge redundancy and introduce gauge-adapted coordinates that separate invariant and scale-imbalance directions. Inspired by gauge fixing in field theory, we introduce a soft orbit-selection (norm-balancing) functional acting only on redundant scale coordinates. We show analytically that it induces dissipative relaxation of imbalance modes to preserve the realized function. In controlled experiments, this orbit-selection penalty expands the stable learning-rate regime and suppresses scale drift without changing expressivity. These results establish a structural link between gauge-orbit geometry and optimization conditioning, providing a concrete connection between gauge-theoretic concepts and machine learning.
title Scale redundancy and soft gauge fixing in positively homogeneous neural networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.14729