LoRA vs. Full Fine-Tuning: A Theoretical Perspective

• URL: http://arxiv.org/abs/2605.19018v1
• Date: Mon, 18 May 2026 18:40:24 GMT
• Title: LoRA vs. Full Fine-Tuning: A Theoretical Perspective
• Abstract summary: Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that reduces memory and computation costs.<n>We study LoRA in a simple linear regression setting and compare its excess risk with that of full fine-tuning.<n>Our theory predicts that LoRA can outperform full fine-tuning when the difference between the pretraining and the downstream tasks is effectively low-rank.
• Score: 29.827767726672523
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Fine-tuning adapts a pre-trained model to downstream tasks using a small amount of labeled data. Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that reduces memory and computation costs while often achieving performance close to full fine-tuning. Despite its widespread use, the theoretical behavior of LoRA is not yet well understood. In this paper, we study LoRA in a simple linear regression setting and compare its excess risk with that of full fine-tuning. Our analysis identifies regimes in which LoRA achieves lower excess risk than full fine-tuning in both overdetermined and underdetermined settings. Specifically, our theory predicts that LoRA can outperform full fine-tuning when the difference between the pretraining and the downstream tasks is effectively low-rank. We further show how the choice of LoRA rank affects generalization performance, explaining why using a very small rank can improve test accuracy in certain settings, even though it limits model expressivity. Finally, we support our theoretical results with experiments on practical tasks, suggesting that the identified tradeoffs and insights extend beyond linear regression.

Related papers

• Beyond LoRA: Is Sparsity-Induced Adaptation Better? [10.18127129139535]
  Low-rank adaptation (LoRA) and its variants provide a memory-matched and compute-efficient alternative to full fine-tuning of pre-trained models.<n>We present a historical framing, covering the past (full fine-tuning and original LoRA), the present (different variants of LoRA) and propose simpler, cheaper, parameter-efficient extensions.<n>We evaluate 11 fine-tuning methods across 10 pre-trained models and 14 datasets, analyzing the fine-tuned models' performance and generalization using tools such as loss landscapes and spectral analysis.
  arXiv  Detail & Related papers  (2026-06-11T17:59:01Z)
• Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation [85.89510825889168]
  We introduce LoRA-Pre, a novel low-rank system for efficient pre-training.<n>LoRA-Pre decomposing the momentum matrix into a compact low-rank subspace within the online linear learner.<n>We empirically validate LoRA-Pre's efficacy by pre-training models from the Llama architecture family.
  arXiv  Detail & Related papers  (2026-02-27T18:57:06Z)
• Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update [50.36542772932594]
  Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights.<n>There is still a gap between full training with low-rank projections (SVDLoRA) and LoRA fine-tuning, indicating that LoRA steps can be further improved.
  arXiv  Detail & Related papers  (2025-09-24T10:32:50Z)
• LoRA Is Slower Than You Think [0.0]
  Low-Rank Adaptation (LoRA) is one of the most widely used techniques for fine-tuning large language models (LLMs)<n>By introducing a small number of trainable low-rank weight matrices, LoRA substantially reduces the number of parameters that need to be updated.<n>We observed that LoRA does not consistently provide speed improvements across all model architectures and training setups.
  arXiv  Detail & Related papers  (2025-07-06T08:36:43Z)
• LoRA vs Full Fine-tuning: An Illusion of Equivalence [73.5303340531806]
  We study how Low-Rank Adaptation (LoRA) and full-finetuning change pre-trained models.<n>We find that LoRA and full fine-tuning yield weight matrices whose singular value decompositions exhibit very different structure.<n>We extend the finding that LoRA forgets less than full fine-tuning and find its forgetting is vastly localized to the intruder dimension.
  arXiv  Detail & Related papers  (2024-10-28T17:14:01Z)
• Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation [58.288682735160585]
  Low-Rank Adaptation (LoRA) is a popular technique for finetuning models. LoRA often under performs when compared to full- parameter fine-tuning. We present a framework that rigorously analyzes the adaptation rates of LoRA methods.
  arXiv  Detail & Related papers  (2024-10-10T18:51:53Z)
• LoRA-Pro: Are Low-Rank Adapters Properly Optimized? [121.0693322732454]
  Low-rank adaptation, also known as LoRA, has emerged as a prominent method for parameter-efficient fine-tuning of foundation models.<n>Despite its computational efficiency, LoRA still yields inferior performance compared to full fine-tuning.<n>We introduce LoRA-Pro, a method that enhances LoRA's performance by strategically adjusting the gradients of low-rank matrices.
  arXiv  Detail & Related papers  (2024-07-25T17:57:12Z)
• LoRA Learns Less and Forgets Less [25.09261710396838]
  Low-Rank Adaptation (LoRA) is a widely-used parameter-efficient finetuning method for large language models. We compare the performance of LoRA and full finetuning on two target domains, programming and mathematics.
  arXiv  Detail & Related papers  (2024-05-15T19:27:45Z)
• LoRA Dropout as a Sparsity Regularizer for Overfitting Control [18.992276878667997]
  We propose a LoRA Dropout mechanism for the LoRA-based methods. We show that appropriate sparsity would help tighten the gap between empirical and generalization risks.
  arXiv  Detail & Related papers  (2024-04-15T09:32:12Z)
• 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)

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.