paper-with-me

홈 › Papers

AdaFish: Fast low-rank parameter-efficient fine-tuning by using second-order information

2024-03-19 · Jiang Hu, Quanzheng Li

Recent advancements in large-scale pretrained models have significantly improved performance across a variety of tasks in natural language processing and computer vision. However, the extensive number of parameters in these models necessitates substantial memory and computational resources for full training. To adapt these models for downstream tasks or specific application-oriented datasets, parameter-efficient fine-tuning methods leveraging pretrained parameters have gained considerable attention. However, it can still be time-consuming due to lots of parameters and epochs. In this work, we introduce AdaFish, an efficient algorithm of the second-order type designed to expedite the training process within low-rank decomposition-based fine-tuning frameworks. Our key observation is that the associated generalized Fisher information matrix is either low-rank or extremely small-scaled. Such a generalized Fisher information matrix is shown to be equivalent to the Hessian matrix. Moreover, we prove the global convergence of AdaFish, along with its iteration/oracle complexity. Numerical experiments show that our algorithm is quite competitive with the state-of-the-art AdamW method.

📄 PDF Abstract BibTeX arXiv:2403.13128

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Methods 이 논문이 사용한 방법론

AdamW AdamW is a stochastic optimization method that modifies the typical implementation of weight decay in Adam, by decoupling [weight…

Similar Papers 제목 키워드 기반

AdaFisher: Adaptive Second Order Optimization via Fisher Information

2024-05-26 · Damien Martins Gomes, Yanlei Zhang, Eugene Belilovsky, Guy Wolf 외

First-order optimization methods are currently the mainstream in training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by employing the diagonal matrix preconditioning of th…

Computational Efficiencyimage-classificationImage ClassificationLanguage Modeling+1

Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information Analysis

2025-04-26 · Damien Martins Gomes

First-order optimization methods remain the standard for training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by preconditioning the stochastic gradient with a diagonal mat…

Computational Efficiencyimage-classificationImage ClassificationLanguage Modeling+2

Fast Forwarding Low-Rank Training

2024-09-06 · Adir Rahamim, Naomi Saphra, Sara Kangaslahti, Yonatan Belinkov

Parameter efficient finetuning methods like low-rank adaptation (LoRA) aim to reduce the computational costs of finetuning pretrained Language Models (LMs). Enabled by these low-rank settings, we propose an even more eff…

FRoD: Full-Rank Efficient Fine-Tuning with Rotational Degrees for Fast Convergence

2025-12-29 · Guoan Wan, Tianyu Chen, Fangzheng Feng, Haoyi Zhou 외 arxiv

Parameter-efficient fine-tuning (PEFT) methods have emerged as a practical solution for adapting large foundation models to downstream tasks, reducing computational and memory costs by updating only a small subset of par…

parameter-efficient fine-tuning

Parameter Efficient Fine-tuning via Explained Variance Adaptation

2024-10-09 · Fabian Paischer, Lukas Hauzenberger, Thomas Schmied, Benedikt Alkin 외

Foundation models (FMs) are pre-trained on large-scale datasets and then fine-tuned for a specific downstream task. The most common fine-tuning method is to update pretrained weights via low-rank adaptation (LoRA). Exist…

Allimage-classificationImage Classificationparameter-efficient fine-tuning+1