paper-with-me

Papers

Data-freeWeight Compress and Denoise for Large Language Models

2024-02-26 · Runyu Peng, Yunhua Zhou, Qipeng Guo, Yang Gao, Hang Yan, Xipeng Qiu, Dahua Lin

Large Language Models (LLMs) are reshaping the research landscape in artificial intelligence, particularly as model parameters scale up significantly, unlocking remarkable capabilities across various domains. Nevertheless, the scalability of model parameters faces constraints due to limitations in GPU memory and computational speed. To address these constraints, various weight compression methods have emerged, such as Pruning and Quantization. Given the low-rank nature of weight matrices in language models, the reduction of weights through matrix decomposition undoubtedly holds significant potential and promise. In this paper, drawing upon the intrinsic structure of LLMs, we propose a novel approach termed Data-free Joint Rank-k Approximation for compressing the parameter matrices. Significantly, our method is characterized by without necessitating additional involvement of any corpus, while simultaneously preserving orthogonality in conjunction with pruning and quantization methods. We achieve a model pruning of 80% parameters while retaining 93.43% of the original performance without any calibration data. Additionally, we explore the fundamental properties of the weight matrix of LLMs undergone Rank-k Approximation and conduct comprehensive experiments to elucidate our hypothesis.

📄 PDF Abstract BibTeX arXiv:2402.16319

Code (0)

등록된 구현이 없습니다.

Tasks

GPUQuantization

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Zero-shot denoising via neural compression: Theoretical and algorithmic framework

2025-06-15 · Ali Zafari, Xi Chen, Shirin Jalali

Zero-shot denoising aims to denoise observations without access to training samples or clean reference images. This setting is particularly relevant in practical imaging scenarios involving specialized domains such as me…

Denoising

Compression of user generated content using denoised references

2022-03-07 · Eduardo Pavez, Enrique Perez, Xin Xiong, Antonio Ortega 외

Video shared over the internet is commonly referred to as user generated content (UGC). UGC video may have low quality due to various factors including previous compression. UGC video is uploaded by users, and then it is…

Denoising

From Denoising to Compressed Sensing

2014-06-16 · Christopher A. Metzler, Arian Maleki, Richard G. Baraniuk

A denoising algorithm seeks to remove noise, errors, or perturbations from a signal. Extensive research has been devoted to this arena over the last several decades, and as a result, today's denoisers can effectively rem…

compressed sensingDenoising

Provable Convergence of Plug-and-Play Priors with MMSE denoisers

2020-05-15 · Xiaojian Xu, Yu Sun, Jiaming Liu, Brendt Wohlberg 외

Plug-and-play priors (PnP) is a methodology for regularized image reconstruction that specifies the prior through an image denoiser. While PnP algorithms are well understood for denoisers performing maximum a posteriori …

Compressive SensingImage Reconstruction

Score-Based Turbo Message Passing for Plug-and-Play Compressive Image Recovery

2025-03-28 · Chang Cai, Xiaojun Yuan, Ying-Jun Angela Zhang

Message passing algorithms have been tailored for compressive imaging applications by plugging in different types of off-the-shelf image denoisers. These off-the-shelf denoisers mostly rely on some generic or hand-crafte…

Denoising