Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models
- URL: http://arxiv.org/abs/2402.02347v3
- Date: Wed, 5 Jun 2024 06:36:45 GMT
- Title: Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models
- Authors: Fangzhao Zhang, Mert Pilanci,
- Abstract summary: Low-Rank Adaptation (LoRA) emerges as a popular parameter-efficient fine-tuning (PEFT) method.
In this work, we study the enhancement of LoRA training by introducing an $r times r$ preconditioner in each gradient step.
- Score: 45.72323731094864
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Low-Rank Adaptation (LoRA) emerges as a popular parameter-efficient fine-tuning (PEFT) method, which proposes to freeze pretrained model weights and update an additive low-rank trainable matrix. In this work, we study the enhancement of LoRA training by introducing an $r \times r$ preconditioner in each gradient step where $r$ is the LoRA rank. We theoretically verify that the proposed preconditioner stabilizes feature learning with LoRA under infinite-width NN setting. Empirically, the implementation of this new preconditioner requires a small change to existing optimizer code and creates virtually minuscule storage and runtime overhead. Our experimental results with both large language models and text-to-image diffusion models show that with this new preconditioner, the convergence and reliability of SGD and AdamW can be significantly enhanced. Moreover, the training process becomes much more robust to hyperparameter choices such as learning rate. The new preconditioner can be derived from a novel Riemannian metric in low-rank matrix field. Code can be accessed at https://github.com/pilancilab/Riemannian_Preconditioned_LoRA.
Related papers
- SBoRA: Low-Rank Adaptation with Regional Weight Updates [19.979815469273476]
This paper introduces Standard Basis LoRA (SBoRA), a novel parameter-efficient fine-tuning approach for Large Language Models.
SBoRA builds upon the pioneering works of Low-Rank Adaptation (LoRA) and Orthogonal Adaptation.
Our results demonstrate the superiority of SBoRA-FA over LoRA in various fine-tuning tasks.
arXiv Detail & Related papers (2024-07-07T15:37:13Z) - DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution [28.589498108609202]
Low-Rank Adaptation (LoRA) relies on a bypass framework that ignores the differential parameter budget requirements across weight matrices.
DoRA decomposes high-rank LoRA layers into structured single-rank components, allowing for dynamic pruning of parameter budget.
Experimental results demonstrate that DoRA can achieve competitive performance compared with LoRA and full model fine-tuning.
arXiv Detail & Related papers (2024-05-27T17:02:27Z) - MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning [105.11844150736536]
Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models.
We propose a new method called MoRA, which employs a square matrix to achieve high-rank updating while maintaining the same number of trainable parameters.
Our method outperforms LoRA on memory-intensive tasks and achieves comparable performance on other tasks.
arXiv Detail & Related papers (2024-05-20T15:48:32Z) - DoRA: Weight-Decomposed Low-Rank Adaptation [57.68678247436207]
We introduce a novel weight decomposition analysis to investigate the inherent differences between FT and LoRA.
Aiming to resemble the learning capacity of FT from the findings, we propose Weight-Decomposed Low-Rank Adaptation (DoRA)
DoRA decomposes the pre-trained weight into two components, magnitude and direction, for fine-tuning.
arXiv Detail & Related papers (2024-02-14T17:59:34Z) - Flora: Low-Rank Adapters Are Secretly Gradient Compressors [30.224822087562163]
Low-rank adaptation (LoRA) is proposed to reduce the optimization states by training fewer parameters.
LoRA restricts overall weight update matrices to be low-rank, limiting the model performance.
We propose Flora, which is able to achieve high-rank updates by resampling the projection matrices.
arXiv Detail & Related papers (2024-02-05T18:50:39Z) - Chain of LoRA: Efficient Fine-tuning of Language Models via Residual
Learning [31.036465632204663]
We introduce Chain of LoRA, an iterative optimization framework inspired by the Frank-Wolfe algorithm.
We demonstrate that COLA can consistently outperform LoRA without additional computational or memory costs.
arXiv Detail & Related papers (2024-01-08T14:26:49Z) - Sparse Low-rank Adaptation of Pre-trained Language Models [79.74094517030035]
We introduce sparse low-rank adaptation (SoRA) that enables dynamic adjustments to the intrinsic rank during the adaptation process.
Our approach strengthens the representation power of LoRA by initializing it with a higher rank, while efficiently taming a temporarily increased number of parameters.
Our experimental results demonstrate that SoRA can outperform other baselines even with 70% retained parameters and 70% training time.
arXiv Detail & Related papers (2023-11-20T11:56:25Z) - The Expressive Power of Low-Rank Adaptation [11.371811534310078]
Low-Rank Adaptation, a parameter-efficient fine-tuning method, has emerged as a prevalent technique for fine-tuning pre-trained models.
This paper takes the first step to bridge the gap by theoretically analyzing the expressive power of LoRA.
For Transformer networks, we show any model can be adapted to a target model of the same size with rank-$(fractextembedding size2)$ LoRA.
arXiv Detail & Related papers (2023-10-26T16:08:33Z) - AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning [143.23123791557245]
Fine-tuning large pre-trained language models on downstream tasks has become an important paradigm in NLP.
We propose AdaLoRA, which adaptively allocates the parameter budget among weight matrices according to their importance score.
We conduct extensive experiments with several pre-trained models on natural language processing, question answering, and natural language generation to validate the effectiveness of AdaLoRA.
arXiv Detail & Related papers (2023-03-18T22:36:25Z) - LoRA: Low-Rank Adaptation of Large Language Models [71.75808607987281]
Low-Rank Adaptation, or LoRA, freezes the pre-trained model weights and injects trainable rank decomposition into each layer of the Transformer architecture.
For GPT-3, LoRA can reduce the number of trainable parameters by 10,000 times and the computation hardware requirement by 3 times compared to full fine-tuning.
arXiv Detail & Related papers (2021-06-17T17:37:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.