Saved in:
Bibliographic Details
Main Authors: Rausch, Roman, Jansen, David, Singh, Sukhbinder, Orús, Román
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.03062
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918229561049088
author Rausch, Roman
Jansen, David
Singh, Sukhbinder
Orús, Román
author_facet Rausch, Roman
Jansen, David
Singh, Sukhbinder
Orús, Román
contents Large Language Models (LLMs) are very demanding in terms of their computational resources. Low-rank decompositions of LLM weights, e.g. via Singular Value Decomposition (SVD), is a promising approach for LLM compression, but presents several practical hurdles, e.g. selecting appropriate layer-wise ranks and getting rid of its parameter redundancy. In this work, we present two physics-inspired improvements to SVD LLM compression: (1) \textbf{FermiGrad}, a gradient-descent algorithm that determines globally optimal layer-wise ranks by relaxing the discrete singular-value truncation into a continuous optimization using the Fermi function; (2) \textbf{PivGa}, an additional \textit{lossless} compression of the low-rank factors that exploits the intrinsic gauge freedom in their parametrization.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03062
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Globally optimized SVD compression of LLMs via Fermi-function-based rank selection and gauge fixing
Rausch, Roman
Jansen, David
Singh, Sukhbinder
Orús, Román
Machine Learning
Large Language Models (LLMs) are very demanding in terms of their computational resources. Low-rank decompositions of LLM weights, e.g. via Singular Value Decomposition (SVD), is a promising approach for LLM compression, but presents several practical hurdles, e.g. selecting appropriate layer-wise ranks and getting rid of its parameter redundancy. In this work, we present two physics-inspired improvements to SVD LLM compression: (1) \textbf{FermiGrad}, a gradient-descent algorithm that determines globally optimal layer-wise ranks by relaxing the discrete singular-value truncation into a continuous optimization using the Fermi function; (2) \textbf{PivGa}, an additional \textit{lossless} compression of the low-rank factors that exploits the intrinsic gauge freedom in their parametrization.
title Globally optimized SVD compression of LLMs via Fermi-function-based rank selection and gauge fixing
topic Machine Learning
url https://arxiv.org/abs/2512.03062