Quantization Operator

Quantization is a model compression technique that reduces the precision of numerical representations in neural networks, aiming to decrease computational costs and memory footprint while preserving model accuracy. Current research focuses on applying quantization to various deep learning architectures, including Vision Transformers (ViTs), large language models (LLMs), and diffusion models, often employing post-training quantization (PTQ) methods to avoid retraining the entire model. This work is significant because it enables the deployment of large, computationally expensive models on resource-constrained devices, impacting fields like healthcare, edge computing, and natural language processing by making advanced AI more accessible and efficient.

Papers

January 10, 2024

Correlated Quantization for Faster Nonconvex Distributed Optimization
Andrei Panferov, Yury Demidovich, Ahmad Rammal, Peter Richtárik
Optimization Purpose Quantization Operator Nonconvex Optimization Non Convex Optimization Communication Complexity Quantization Aware

January 9, 2024

EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models
Xuewen Liu, Zhikai Li, Junrui Xiao, Qingyi Gu
Diffusion Model Fine Grained Quantization Operator Post Training Quantization Distribution Alignment Denoising Model

December 23, 2023

Efficient Asynchronous Federated Learning with Sparsification and Quantization
Juncheng Jia, Ji Liu, Chendi Zhou, Hao Tian, Mianxiong Dong, Dejing Dou
Quantization Operator Random Sparsification Asynchronous Federated Learning Asynchronous Execution

December 20, 2023

Towards Efficient Verification of Quantized Neural Networks
Pei Huang, Haoze Wu, Yuting Yang, Ieva Daukantas, Min Wu, Yedi Zhang, Clark Barrett
Quantization Operator Device Inference Quantized Neural Network Efficient Verification Bound Propagation Perception Network

December 17, 2023

Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting
Dawei Yang, Ning He, Xing Hu, Zhihang Yuan, Jiangyong Yu, Chen Xu, Zhe Jiang
Quantization Operator Multiplier Free Quantization Coarse to Fine Quantization Error Network Quantization Structural Re Parameterization Weight Decomposition

December 13, 2023

USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models
Shaojin Ding, David Qiu, David Rim, Yanzhang He, Oleg Rybakov, Bo Li, Rohit Prabhavalkar, Weiran Wang, Tara N. Sainath, Zhonglin Han, Jian Li, Amir Yazdanbakhsh, Shivani Agrawal
Automatic Speech Recognition Fine Tuning Speech Recognition Model Compression Quantization Operator Automatic Speech Recognition Model Universal Speech Model

December 10, 2023

FP8-BERT: Post-Training Quantization for Transformer
Jianwei Li, Tianchi Zhang, Ian En-Hsu Yen, Dongkuan Xu
Transformer Based BERT Model Ticket BERT Quantization Operator Quantization Aware Training BERT Variant 8 Bit Quantization

December 7, 2023

GenQ: Quantization in Low Data Regimes with Generative Synthetic Data
Yuhang Li, Youngeun Kim, Donghyun Lee, Souvik Kundu, Priyadarshini Panda
Generative Model Synthetic Data Quantization Operator Low Bit Quantization Low Data Regime Gradient Quantization

November 22, 2023

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization
Prateek Yadav, Leshem Choshen, Colin Raffel, Mohit Bansal
Language Model Parameter Efficient Fine Tuning Quantization Operator Linear Compression Compositional Generalization Random Sparsification Parameter Update Shot Generalization

November 21, 2023

Shedding the Bits: Pushing the Boundaries of Quantization with Minifloats on FPGAs
Shivam Aggarwal, Hans Jakob Damsgaard, Alessandro Pappalardo, Giuseppe Franco, Thomas B. Preußer, Michaela Blott, Tulika Mitra
Quantization Operator Field Programmable Gate Array Post Training Quantization Document Boundary Quantization Technique P Bit Floating Point Format

November 16, 2023

How Does Calibration Data Affect the Post-training Pruning and Quantization of Large Language Models?
Miles Williams, Nikolaos Aletras
Large Language Model Model Compression Quantization Operator LLM Quantization Calibration Data

November 2, 2023

October 17, 2023

TEQ: Trainable Equivalent Transformation for Quantization of LLMs
Wenhua Cheng, Yiyang Cai, Kaokao Lv, Haihao Shen
Large Language Model Quantization Operator Low Precision Quantization Learning Transformation

October 12, 2023

October 5, 2023

Robustness-Guided Image Synthesis for Data-Free Quantization
Jianhong Bai, Yuchen Yang, Huanpeng Chu, Hualiang Wang, Zuozhu Liu, Ruizhe Chen, Xiaoxuan He, Lianrui Mu, Chengfei Cai, Haoji Hu
Image Synthesis Quantization Operator Data Free Quantization Image Speak

September 30, 2023

Quantization of Deep Neural Networks to facilitate self-correction of weights on Phase Change Memory-based analog hardware
Arseni Ivanov
Deep Neural Network Quantization Operator Phase Transition Neural Network Weight Self Correction Analog Computing Self Improving Analog Layout

September 25, 2023

On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks "In-the-Wild''
Arthur Pimentel, Heitor Guimarães, Anderson R. Avila, Mehdi Rezagholizadeh, Tiago H. Falk
Self Supervised Learning Global Impact Quantization Operator Edge Pruning Speech Recognition System Self Supervised Speech Model Speech Recognition Accuracy Speech Recognition Task Edge Speech Application

September 22, 2023

Poster: Self-Supervised Quantization-Aware Knowledge Distillation
Kaiqi Zhao, Ming Zhao
Self Supervised Quantization Operator Quantization Aware Training Visually Effective Poster Quantization Aware Knowledge Distillation Quantization Function

Quantization Operator

Papers

Correlated Quantization for Faster Nonconvex Distributed Optimization

EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models

Efficient Asynchronous Federated Learning with Sparsification and Quantization

Towards Efficient Verification of Quantized Neural Networks

Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting

USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models

FP8-BERT: Post-Training Quantization for Transformer

GenQ: Quantization in Low Data Regimes with Generative Synthetic Data

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization

Shedding the Bits: Pushing the Boundaries of Quantization with Minifloats on FPGAs

How Does Calibration Data Affect the Post-training Pruning and Quantization of Large Language Models?

AWEQ: Post-Training Quantization with Activation-Weight Equalization for Large Language Models

Effective Quantization for Diffusion Models on CPUs

TEQ: Trainable Equivalent Transformation for Quantization of LLMs

LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models

A Carbon Tracking Model for Federated Learning: Impact of Quantization and Sparsification

Robustness-Guided Image Synthesis for Data-Free Quantization

Quantization of Deep Neural Networks to facilitate self-correction of weights on Phase Change Memory-based analog hardware

On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks "In-the-Wild''

Poster: Self-Supervised Quantization-Aware Knowledge Distillation