English
Related papers

Related papers: Retraining-Based Iterative Weight Quantization for…

200 papers

Quantization of deep neural networks is a promising approach that reduces the inference cost, making it feasible to run deep networks on resource-restricted devices. Inspired by existing methods, we propose a new framework to learn the…

Machine Learning · Computer Science 2022-02-28 Amir Ardakani , Arash Ardakani , Brett Meyer , James J. Clark , Warren J. Gross

Quantization is a widely used compression method that effectively reduces redundancies in over-parameterized neural networks. However, existing quantization techniques for deep neural networks often lack a comprehensive error analysis due…

Machine Learning · Computer Science 2023-09-21 Jinjie Zhang , Rayan Saab

With the commercialization of large language models (LLMs), weight-activation quantization has emerged to compress and accelerate LLMs, achieving high throughput while reducing inference costs. However, existing post-training quantization…

Machine Learning · Computer Science 2025-02-11 Jung Hyun Lee , Jeonghoon Kim , June Yong Yang , Se Jung Kwon , Eunho Yang , Kang Min Yoo , Dongsoo Lee

In this paper we present a simple and computationally efficient quantization scheme that enables us to reduce the resolution of the parameters of a neural network from 32-bit floating point values to 8-bit integer values. The proposed…

Machine Learning · Computer Science 2016-12-20 Raziel Alvarez , Rohit Prabhavalkar , Anton Bakhtin

Deep neural networks (DNNs) have recently achieved great success in many visual recognition tasks. However, existing deep neural network models are computationally expensive and memory intensive, hindering their deployment in devices with…

Machine Learning · Computer Science 2020-06-16 Yu Cheng , Duo Wang , Pan Zhou , Tao Zhang

Learned image compression has a problem of non-bit-exact reconstruction due to different calculations of floating point arithmetic on different devices. This paper shows a method to achieve a deterministic reconstructed image by quantizing…

Image and Video Processing · Electrical Eng. & Systems 2024-01-12 Esin Koyuncu , Timofey Solovyev , Johannes Sauer , Elena Alshina , André Kaup

Conventional model compression techniques for LLMs address high memory consumption and slow inference challenges but typically require computationally expensive retraining to preserve accuracy. In contrast, one-shot compression methods…

Machine Learning · Computer Science 2025-08-18 Mohammad Mozaffari , Amir Yazdanbakhsh , Maryam Mehri Dehnavi

Model compression techniques, such as pruning and quantization, are becoming increasingly important to reduce the memory footprints and the amount of computations. Despite model size reduction, achieving performance enhancement on devices…

Machine Learning · Computer Science 2020-03-06 Se Jung Kwon , Dongsoo Lee , Byeongwook Kim , Parichay Kapoor , Baeseong Park , Gu-Yeon Wei

As Deep Neural Networks (DNNs) usually are overparameterized and have millions of weight parameters, it is challenging to deploy these large DNN models on resource-constrained hardware platforms, e.g., smartphones. Numerous network…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Peng Hu , Xi Peng , Hongyuan Zhu , Mohamed M. Sabry Aly , Jie Lin

Deep neural networks (DNNs) can be made hardware-efficient by reducing the numerical precision of the weights and activations of the network and by improving the network's resilience to noise. However, this gain in efficiency often comes at…

Weight-sharing quantization has emerged as a technique to reduce energy expenditure during inference in large neural networks by constraining their weights to a limited set of values. However, existing methods for weight-sharing…

Machine Learning · Computer Science 2023-10-05 Christopher Subia-Waud , Srinandan Dasmahapatra

Binary quantization approaches, which replace weight matrices with binary matrices and substitute costly multiplications with cheaper additions, offer a computationally efficient approach to address the increasing computational and storage…

Machine Learning · Computer Science 2026-03-03 Vladimír Boža , Vladimír Macko

Post-training quantization (PTQ) has emerged as a promising technique for mitigating memory consumption and computational costs in large language models (LLMs). However, a systematic examination of various quantization schemes, model…

Machine Learning · Computer Science 2023-05-29 Zhewei Yao , Xiaoxia Wu , Cheng Li , Stephen Youn , Yuxiong He

As neural networks gain widespread adoption in embedded devices, there is a need for model compression techniques to facilitate deployment in resource-constrained environments. Quantization is one of the go-to methods yielding…

Machine Learning · Computer Science 2021-01-13 Karina Vasquez , Yeshwanth Venkatesha , Abhiroop Bhattacharjee , Abhishek Moitra , Priyadarshini Panda

Quantizing a floating-point neural network to its fixed-point representation is crucial for Learned Image Compression (LIC) because it improves decoding consistency for interoperability and reduces space-time complexity for implementation.…

Image and Video Processing · Electrical Eng. & Systems 2023-10-10 Junqi Shi , Ming Lu , Zhan Ma

Integer quantization of neural networks can be defined as the approximation of the high precision computation of the canonical neural network formulation, using reduced integer precision. It plays a significant role in the efficient…

Machine Learning · Computer Science 2021-01-15 Jian Li , Raziel Alvarez

The state-of-the-art performance for several real-world problems is currently reached by convolutional neural networks (CNN). Such learning models exploit recent results in the field of deep learning, typically leading to highly performing,…

Machine Learning · Computer Science 2021-08-31 Giosuè Cataldo Marinò , Alessandro Petrini , Dario Malchiodi , Marco Frasca

Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the training instability in long short-term memory (LSTM)…

We propose DiffQ a differentiable method for model compression for quantizing model parameters without gradient approximations (e.g., Straight Through Estimator). We suggest adding independent pseudo quantization noise to model parameters…

Machine Learning · Statistics 2022-10-18 Alexandre Défossez , Yossi Adi , Gabriel Synnaeve

Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and…

Machine Learning · Computer Science 2024-09-04 Yelysei Bondarenko , Riccardo Del Chiaro , Markus Nagel