paper-with-me

Papers

Post-Optimization Adaptive Rank Allocation for LoRA

2026-04-30 · Vishnuprasadh Kumaravelu, Sunil Gupta, P. K. Srijith arxiv

Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a parameter-efficient fine-tuning technique. However, standard LoRA implementations disregard the varying intrinsic dimensionality of model layers and enforce a uniform rank, leading to parameter redundancy. We propose Post-Optimization Adaptive Rank Allocation (PARA), a data-free compression method for LoRA that integrates seamlessly into existing fine-tuning pipelines. PARA leverages Singular Value Decomposition to prune LoRA ranks using a global threshold over singular values across all layers. This results in non-uniform rank allocation based on layer-wise spectral importance. As a post-hoc method, PARA circumvents the training modifications and resulting instabilities that dynamic architectures typically incur. We empirically demonstrate that PARA reduces parameter count by 75-90\% while preserving the predictive performance of the original, uncompressed LoRA across multiple vision and language benchmarks. Code will be published upon acceptance.

📄 PDF Abstract BibTeX arXiv:2604.27796

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning

2026-06-28 · Zhibin Duan, Yuhong Wang, Jiahong Fu, Zongsheng Yue 외 arxiv

While Low-rank adaptation (LoRA) enables highly efficient fine-tuning by constraining task-specific updates to fixed low-rank subspaces, this rigid design limits representational flexibility and often results in overconf…

parameter-efficient fine-tuningTopic Models

When Gradient Importance Lies: Adaptive LoRA Rank Allocation Fails Under GRPO

2026-05-08 · Yash Ganpat Sawant arxiv

Adaptive rank allocation for LoRA - allocating more parameters to important layers and fewer to unimportant ones - consistently improves efficiency under supervised fine-tuning (SFT). We test whether this success transfe…

Reinforcement Learning

IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware Scoring

2026-03-14 · Xuan Cui, Huiyue Li, Run Zeng, Yunfei Zhao 외 arxiv

As large language models (LLMs) scale to billions of parameters, full-parameter fine-tuning becomes compute- and memory-prohibitive. Parameter-efficient fine-tuning (PEFT) mitigates this issue by updating only a small se…

parameter-efficient fine-tuning

RSRA: Training-Free Probing of Representation Sensitivity for Efficient LoRA Rank Allocation

2026-07-05 · Jiaqi Liu, Haidong Kang, Qihui Zhao, Guo Yu 외 arxiv

Parameter-efficient fine-tuning enables large language models to adapt to downstream tasks with substantially lower computational and storage cost, and Low-Rank Adaptation (LoRA) is among its most widely used techniques.…

ARD-LoRA: Dynamic Rank Allocation for Parameter-Efficient Fine-Tuning of Foundation Models with Heterogeneous Adaptation Needs

2025-06-23 · Haseeb Ullah Khan Shinwari, Muhammad Usama

Conventional Low-Rank Adaptation (LoRA) methods employ a fixed rank, imposing uniform adaptation across transformer layers and attention heads despite their heterogeneous learning dynamics. This paper introduces Adaptive…

parameter-efficient fine-tuning