Linear Quantization

Linear quantization is a technique for reducing the memory footprint and computational cost of neural networks by representing weights and activations using fewer bits, thereby improving efficiency without significant accuracy loss. Current research focuses on developing novel quantization methods, particularly for large language models (LLMs) and resource-constrained devices, often employing techniques like two-stage quantization, optimized scaling factors, and bit-width adaptation across different network components. These advancements are crucial for deploying deep learning models on edge devices and for making large models more accessible, impacting fields ranging from natural language processing to real-time industrial applications.

Papers

August 11, 2024

RTF-Q: Efficient Unsupervised Domain Adaptation with Retraining-free Quantization
Nanyang Du, Chen Tang, Yuxiao Jiang, Yuan Meng, Zhi Wang
Unsupervised Domain Adaptation Quantization Aware Training Linear Quantization

July 3, 2024

GPTQT: Quantize Large Language Models Twice to Push the Efficiency
Yipin Guo, Yilin Lang, Qinyuan Ren
High Efficiency GPT Neo Post Training Quantization Generative Large Language Model Product Quantization Linear Quantization

May 28, 2024

4-bit Shampoo for Memory-Efficient Network Training
Sike Wang, Pan Zhou, Jia Li, Hua Huang
Second Order Adaptive Preconditioner Memory Efficient Linear Quantization

March 4, 2024

FlowPrecision: Advancing FPGA-Based Real-Time Fluid Flow Estimation with Linear Quantization
Tianheng Ling, Julian Hoever, Chao Qian, Gregor Schiele
Soft Sensor Real Time Inference Flow Estimation Linear Quantization Flow Sensor

January 11, 2024

Extreme Compression of Large Language Models via Additive Quantization
Vage Egiazarian, Andrei Panferov, Denis Kuznedelev, Elias Frantar, Artem Babenko, Dan Alistarh
High Compression LLM Compression Open Large Language Model Linear Quantization Multi Codebook

December 20, 2022

Redistribution of Weights and Activations for AdderNet Quantization
Ying Nie, Kai Han, Haikang Diao, Chuanjian Liu, Enhua Wu, Yunhe Wang
Balancing Weight Targeted Activation Penalty Low Bit Quantization P$ Norm Redistribution Mechanism Adder Neural Network Linear Quantization

October 29, 2022

Empirical Evaluation of Post-Training Quantization Methods for Language Tasks
Ting Hu, Christoph Meinel, Haojin Yang
BERT Model Empirical Evaluation Language Task Bit Quantization BERT Large Linear Quantization

July 13, 2022

Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets
Lu Zeng, Sree Hari Krishnan Parthasarathi, Yuzong Liu, Alex Escott, Santosh Kumar Cheekatmalla, Nikko Strom, Shiv Vitaladevuni
Quantization Operator Keyword Spotting Embedded System Quantization Technique Neural Network Accelerator Bit Weight Linear Quantization 8 Bit Quantization

February 18, 2022

LG-LSQ: Learned Gradient Linear Symmetric Quantization
Shih-Ting Lin, Zhaofang Li, Yu-Hsiang Cheng, Hao-Wen Kuo, Chih-Cheng Lu, Kea-Tiong Tang
Quantization Technique Uniform Quantization Linear Quantization Gradient Quantization