Quantization Step

Quantization step, the process of reducing the precision of numerical representations in neural networks, aims to improve model efficiency and reduce computational costs without significant accuracy loss. Current research focuses on optimizing quantization techniques for various model architectures, including large language models and convolutional neural networks, employing methods like post-training quantization (PTQ) and quantization-aware training (QAT), often incorporating gradient-based optimization or novel loss functions to mitigate accuracy degradation. These advancements are crucial for deploying deep learning models on resource-constrained devices and improving the scalability of large models, impacting both the efficiency of machine learning systems and their accessibility across diverse applications.

Papers

October 30, 2024

A Comprehensive Study on Quantization Techniques for Large Language Models
Jiedong Lang, Zhehao Guo, Shuyu Huang
Full Model Large Model Large Language Comprehensive Study Quantization Technique Quantization Step Different Quantization

October 12, 2024

FlatQuant: Flatness Matters for LLM Quantization
Yuxuan Sun, Ruikang Liu, Haoli Bai, Han Bao, Kang Zhao, Yuening Li, Jiaxin Hu, Xianzhi Yu, Lu Hou, Chun Yuan, Xin Jiang, Wulong Liu, Jun Yao
Post Training Quantization Affine Transformation LLM Quantization Quantization Step W4A8 Quantization

June 2, 2024

MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
Aozhong Zhang, Naigang Wang, Yanxia Deng, Xin Li, Zi Yang, Penghang Yin
Post Training Quantization Weight Update Proximal Gradient Descent Preprocessing Method Quantization Step Input Quantization

April 30, 2024

Transition Rate Scheduling for Quantization-Aware Training
Junghyup lee, Dohyung Kim, Jeimin Jeon, Bumsub Ham
Learning Rate Quantization Aware Training Weight Freezing Weight Only Quantization Quantization Step Variable Rate

April 8, 2024

Investigating the Impact of Quantization on Adversarial Robustness
Qun Li, Yuan Meng, Chen Tang, Jiacheng Jiang, Zhi Wang
Adversarial Robustness Global Impact Quantization Operator Post Training Quantization Model Robustness Quantization Aware Training Quantization Step

September 29, 2023

On Uniform Scalar Quantization for Learned Image Compression
Haotian Zhang, Li Li, Dong Liu
Learned Image Compression Quantization Step Scalar Quantization Sharpness Aware Quantization

September 4, 2023

Softmax Bias Correction for Quantized Generative Models
Nilesh Prasad Pandey, Marios Fournarakis, Chirag Patel, Markus Nagel
Post Training Quantization Quantization Step Quantization Noise Quantization Parameter Vector Quantized Generative Adversarial Network Softmax Output

August 24, 2023

Quantized distributed Nash equilibrium seeking under DoS attacks: A quantized consensus based approach
Shuai Feng, Maojiao Ye, Lihua Xie, Shengyuan Xu
Constructive Approach Nash Equilibrium Multiplier Free Quantization Consensus Group Decision Quantization Error Quantization Step Denial of Service Attack

August 15, 2023

Gradient-Based Post-Training Quantization: Challenging the Status Quo
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Quantization Operator Post Training Quantization Quantization Aware Training Chaotic Regime Quantization Step

August 13, 2023

RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networks
Yufei Guo, Xiaode Liu, Yuanpei Chen, Liwen Zhang, Weihang Peng, Yuhan Zhang, Xuhui Huang, Zhe Ma
Neural Network Spiking Neural Network Full Potential Quantization Error Quantization Step Soft Membrane Membrane Potential

August 8, 2023

Quantization Aware Factorization for Deep Neural Network Compression
Daria Cherniuk, Stanislav Abukhovich, Anh-Huy Phan, Ivan Oseledets, Andrzej Cichocki, Julia Gusak
Tensor Decomposition Post Training Quantization Step Tensor Approximation Low Rank Quantization

April 21, 2023

Picking Up Quantization Steps for Compressed Image Classification
Li Ma, Peixi Peng, Guangyao Chen, Yifan Zhao, Siwei Dong, Yonghong Tian
Supervised ImageNet Batch Normalization Compressed Domain Quantization Step

March 13, 2023

Bag of Tricks with Quantized Convolutional Neural Networks for image classification
Jie Hu, Mengze Zeng, Enhua Wu
Image Classification Multiplier Free Quantization Quantization Aware Training Bag Prototype Unconventional Rabbit Hat Trick Quantization Step

March 2, 2023

Ternary Quantization: A Survey
Dan Liu, Xue Liu
Timely Survey Model Quantization Low Bit Quantization Quantization Step Ternary Quantization

December 5, 2022

QFT: Post-training quantization via fast joint finetuning of all degrees of freedom
Alex Finkelstein, Ella Fuchs, Idan Tal, Mark Grobman, Niv Vosco, Eldad Meller
Fine Tuning Post Training Quantization Multiplier Free Quantization Different Degree Freedom Matter Quantization Step Degree of Freedom Parameterized Network Bit Weight Quantization

October 27, 2022

Neural Networks with Quantization Constraints
Ignacio Hounie, Juan Elenter, Alejandro Ribeiro
Neural Network Deep Learning Model Multiplier Free Quantization Constrained Learning Quantization Step

July 7, 2022

Attention Round for Post-Training Quantization
Huabin Diao, Gongyan Li, Shaoyun Xu, Yuexing Hao
Quantization Operator Post Training Quantization Mixed Precision Quantization Attention Head Quantization Step Quantization Performance

June 26, 2022

CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple Quantization Steps
HyunJin Kim, Jungwoo Shin, Alberto A. Del Barrio
Convolutional Neural Network Lightweight Convolutional Neural Network Quantization Step Bit Depth Cyclic Training