paper-with-me

Papers

QERA: an Analytical Framework for Quantization Error Reconstruction

2024-10-08 · Cheng Zhang, Jeffrey T. H. Wong, Can Xiao, George A. Constantinides, Yiren Zhao

he growing number of parameters and computational demands of large language models (LLMs) present significant challenges for their efficient deployment. Recently, there is an increasing interest in quantizing weights to extremely low precision while offsetting the resulting error with low-rank, high-precision error reconstruction terms. The combination of quantization and low-rank approximation is now popular in both adapter-based, parameter-efficient fine-tuning methods such as LoftQ and low-precision inference techniques including ZeroQuant-V2. Usually, the low-rank terms are calculated via the singular value decomposition (SVD) of the weight quantization error, minimizing the Frobenius and spectral norms of the weight approximation error. Recent methods like LQ-LoRA and LQER introduced hand-crafted heuristics to minimize errors in layer outputs (activations) rather than weights, resulting improved quantization results. However, these heuristic methods lack an analytical solution to guide the design of quantization error reconstruction terms. In this paper, we revisit this problem and formulate an analytical framework, named Quantization Error Reconstruction Analysis (QERA), and offer a closed-form solution to the problem. We show QERA benefits both existing low-precision fine-tuning and inference methods -- QERA achieves a fine-tuned accuracy gain of $\Delta_{\text{acc}}$ = 6.05% of 2-bit RoBERTa-base on GLUE compared to LoftQ; and obtains $\Delta_{\text{acc}}$ = 2.97% higher post-training quantization accuracy of 4-bit Llama-3.1-70B on average than ZeroQuant-V2 and $\Delta_{\text{ppl}}$ = - 0.28 lower perplexity on WikiText2 than LQER.

📄 PDF Abstract BibTeX arXiv:2410.06040

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuningQuantization

Similar Papers 제목 키워드 기반

SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization

2026-05-12 · Chengzhu Bao, Xianglong Yan, Zhiteng Li, Guangshuo Qin 외 arxiv

NVFP4 has recently emerged as an efficient 4-bit microscaling format for large language models (LLMs), offering superior numerical fidelity with native hardware support. However, existing methods often yield suboptimal p…

Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs

2026-02-02 · Yoonjun Cho, Dongjae Jeon, Soeun Kim, Moongyu Jeon 외 arxiv

Quantization Error Reconstruction (QER) reduces accuracy loss in Post-Training Quantization (PTQ) by approximating weights as $\mathbf{W} \approx \mathbf{Q} + \mathbf{L}\mathbf{R}$, using a rank-$r$ correction to reconst…

parameter-efficient fine-tuning

Communication-Efficient Federated Learning over Capacity-Limited Wireless Networks

2023-07-20 · Jaewon Yun, Yongjeong Oh, Yo-Seb Jeon, H. Vincent Poor

In this paper, a communication-efficient federated learning (FL) framework is proposed for improving the convergence rate of FL under a limited uplink capacity. The central idea of the proposed framework is to transmit t…

Federated LearningQuantization

SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization

2026-03-09 · Yeonsik Park, Hyeonseong Kim, Seungkyu Choi arxiv

Post-training quantization (PTQ) has emerged as a prevailing technique for deploying large language models (LLMs) efficiently in terms of both memory and computation, across edge devices and server platforms. Existing PT…

GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMs

2026-03-26 · Selim An, Il hong Suh, Yeseong Kim arxiv

Quantization techniques such as BitsAndBytes, AWQ, and GPTQ are widely used as a standard method in deploying large language models but often degrades accuracy when using low-bit representations, e.g., 4 bits. Low-rank c…