Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ichi, A. El, Jbilou, K.
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.17112
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909999714795520
author Ichi, A. El
Jbilou, K.
author_facet Ichi, A. El
Jbilou, K.
contents Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language tasks but suffer from extremely large memory footprints and computational costs. In this paper, we introduce a tensor compression framework based on the cproduct for computing low rank approximation In the first part of our approach, we leverage the algebraic structure of the cproduct to represent weight tensors such as those in embedding layers, attention projections, and feed forward networks in a transform domain where frontal slices can be jointly approximated by low rank tensor factors. This enables computationally efficient compression that exploits multidimensional correlations beyond traditional SVD methods.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17112
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Low-Rank Tensor Approximation of Weights in Large Language Models via Cosine Lanczos Bidiagonalization
Ichi, A. El
Jbilou, K.
Machine Learning
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language tasks but suffer from extremely large memory footprints and computational costs. In this paper, we introduce a tensor compression framework based on the cproduct for computing low rank approximation In the first part of our approach, we leverage the algebraic structure of the cproduct to represent weight tensors such as those in embedding layers, attention projections, and feed forward networks in a transform domain where frontal slices can be jointly approximated by low rank tensor factors. This enables computationally efficient compression that exploits multidimensional correlations beyond traditional SVD methods.
title Low-Rank Tensor Approximation of Weights in Large Language Models via Cosine Lanczos Bidiagonalization
topic Machine Learning
url https://arxiv.org/abs/2601.17112