Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Arcas, Alejandro Moreno, Sanchis, Albert, Civera, Jorge, Juan, Alfons
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.16531
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916943921938432
author Arcas, Alejandro Moreno
Sanchis, Albert
Civera, Jorge
Juan, Alfons
author_facet Arcas, Alejandro Moreno
Sanchis, Albert
Civera, Jorge
Juan, Alfons
contents Adaptation of foundation models using low-rank methods is a widespread approach. Another way to adapt these models is to employ orthogonal fine-tuning methods, which are less time and memory efficient despite their good generalization properties. In this work, we propose Householder Orthogonal Fine-tuning (HOFT), a novel orthogonal fine-tuning method that aims to alleviate time and space complexity. Moreover, some theoretical properties of the orthogonal fine-tuning paradigm are explored. From this exploration, Scaled Householder Orthogonal Fine-tuning (SHOFT) is proposed. Both HOFT and SHOFT are evaluated in downstream tasks, namely commonsense reasoning, machine translation, subject-driven generation and mathematical reasoning. Compared with state-of-the-art adaptation methods, HOFT and SHOFT show comparable or better results.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16531
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HOFT: Householder Orthogonal Fine-tuning
Arcas, Alejandro Moreno
Sanchis, Albert
Civera, Jorge
Juan, Alfons
Machine Learning
Adaptation of foundation models using low-rank methods is a widespread approach. Another way to adapt these models is to employ orthogonal fine-tuning methods, which are less time and memory efficient despite their good generalization properties. In this work, we propose Householder Orthogonal Fine-tuning (HOFT), a novel orthogonal fine-tuning method that aims to alleviate time and space complexity. Moreover, some theoretical properties of the orthogonal fine-tuning paradigm are explored. From this exploration, Scaled Householder Orthogonal Fine-tuning (SHOFT) is proposed. Both HOFT and SHOFT are evaluated in downstream tasks, namely commonsense reasoning, machine translation, subject-driven generation and mathematical reasoning. Compared with state-of-the-art adaptation methods, HOFT and SHOFT show comparable or better results.
title HOFT: Householder Orthogonal Fine-tuning
topic Machine Learning
url https://arxiv.org/abs/2505.16531