RepLoRA: Reparameterizing Low-Rank Adaptation via the Perspective of Mixture of Experts

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Truong, Tuan, Nguyen, Chau, Nguyen, Huy, Le, Minh, Le, Trung, Ho, Nhat
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916783415361536
author Truong, Tuan
Nguyen, Chau
Nguyen, Huy
Le, Minh
Le, Trung
Ho, Nhat
author_facet Truong, Tuan
Nguyen, Chau
Nguyen, Huy
Le, Minh
Le, Trung
Ho, Nhat
contents Low-rank Adaptation (LoRA) has emerged as a powerful method for fine-tuning large-scale foundation models. Despite its popularity, the theoretical understanding of LoRA has remained limited. This paper presents a theoretical analysis of LoRA by examining its connection to the Mixture of Experts models. Under this framework, we show that simple reparameterizations of the LoRA matrices can notably accelerate the low-rank matrix estimation process. In particular, we prove that reparameterization can reduce the data needed to achieve a desired estimation error from an exponential to a polynomial scale. Motivated by this insight, we propose Reparameterized Low-Rank Adaptation (RepLoRA), which incorporates lightweight MLPs to reparameterize the LoRA matrices. Extensive experiments across multiple domains demonstrate that RepLoRA consistently outperforms vanilla LoRA. Notably, with limited data, RepLoRA surpasses LoRA by a margin of up to 40.0% and achieves LoRA's performance with only 30.0% of the training data, highlighting both the theoretical and empirical robustness of our PEFT method.
format Preprint
id arxiv_https___arxiv_org_abs_2502_03044
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RepLoRA: Reparameterizing Low-Rank Adaptation via the Perspective of Mixture of Experts
Truong, Tuan
Nguyen, Chau
Nguyen, Huy
Le, Minh
Le, Trung
Ho, Nhat
Machine Learning
Low-rank Adaptation (LoRA) has emerged as a powerful method for fine-tuning large-scale foundation models. Despite its popularity, the theoretical understanding of LoRA has remained limited. This paper presents a theoretical analysis of LoRA by examining its connection to the Mixture of Experts models. Under this framework, we show that simple reparameterizations of the LoRA matrices can notably accelerate the low-rank matrix estimation process. In particular, we prove that reparameterization can reduce the data needed to achieve a desired estimation error from an exponential to a polynomial scale. Motivated by this insight, we propose Reparameterized Low-Rank Adaptation (RepLoRA), which incorporates lightweight MLPs to reparameterize the LoRA matrices. Extensive experiments across multiple domains demonstrate that RepLoRA consistently outperforms vanilla LoRA. Notably, with limited data, RepLoRA surpasses LoRA by a margin of up to 40.0% and achieves LoRA's performance with only 30.0% of the training data, highlighting both the theoretical and empirical robustness of our PEFT method.
title RepLoRA: Reparameterizing Low-Rank Adaptation via the Perspective of Mixture of Experts
topic Machine Learning
url https://arxiv.org/abs/2502.03044