English
Related papers

Related papers: Post-training Quantization for Neural Networks wit…

200 papers

Model compression has gained a lot of attention due to its ability to reduce hardware resource requirements significantly while maintaining accuracy of DNNs. Model compression is especially useful for memory-intensive recurrent neural…

Machine Learning · Computer Science 2018-05-30 Dongsoo Lee , Byeongwook Kim

Classical neural network approximation results take the form: for every function $f$ and every error tolerance $\epsilon > 0$, one constructs a neural network whose architecture and weights depend on $\epsilon$. This paper introduces a…

Neural and Evolutionary Computing · Computer Science 2025-11-20 Clemens Hutter , Valentin Abadie , Helmut Bölcskei

We present an overview of techniques for quantizing convolutional neural networks for inference with integer weights and activations. Per-channel quantization of weights and per-layer quantization of activations to 8-bits of precision…

Machine Learning · Computer Science 2018-06-22 Raghuraman Krishnamoorthi

Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems.…

Machine Learning · Computer Science 2017-11-15 Hao Li , Soham De , Zheng Xu , Christoph Studer , Hanan Samet , Tom Goldstein

We solve the analysis sparse coding problem considering a combination of convex and non-convex sparsity promoting penalties. The multi-penalty formulation results in an iterative algorithm involving proximal-averaging. We then unfold the…

Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of…

Computer Vision and Pattern Recognition · Computer Science 2018-07-27 Dongqing Zhang , Jiaolong Yang , Dongqiangzi Ye , Gang Hua

Operating deep neural networks (DNNs) on devices with limited resources requires the reduction of their memory as well as computational footprint. Popular reduction methods are network quantization or pruning, which either reduce the word…

This paper examines the use of Quantized Neural Networks (QNNs) for two resource-constrained scientific applications: automated calibration of semi-conductor quantum bits (qubits) and scientific particle detectors. We evaluate the…

With the development of deep neural networks, the size of network models becomes larger and larger. Model compression has become an urgent need for deploying these network models to mobile or embedded devices. Model quantization is a…

Machine Learning · Computer Science 2019-07-02 Wen-Pu Cai , Wu-Jun Li

Lately, post-training quantization methods have gained considerable attention, as they are simple to use, and require only a small unlabeled calibration set. This small dataset cannot be used to fine-tune the model without significant…

Machine Learning · Computer Science 2020-12-15 Itay Hubara , Yury Nahshan , Yair Hanani , Ron Banner , Daniel Soudry

Similar to convolution neural networks, recurrent neural networks (RNNs) typically suffer from over-parameterization. Quantizing bit-widths of weights and activations results in runtime efficiency on hardware, yet it often comes at the cost…

Machine Learning · Computer Science 2017-10-30 Supriya Kapur , Asit Mishra , Debbie Marr

Reducing bit-widths of weights, activations, and gradients of a Neural Network can shrink its storage size and memory usage, and also allow for faster training and inference by exploiting bitwise operations. However, previous attempts for…

Machine Learning · Computer Science 2016-12-01 Qinyao He , He Wen , Shuchang Zhou , Yuxin Wu , Cong Yao , Xinyu Zhou , Yuheng Zou

At present, the quantification methods of neural network models are mainly divided into post-training quantization (PTQ) and quantization aware training (QAT). Post-training quantization only need a small part of the data to complete the…

Machine Learning · Computer Science 2022-07-08 Huabin Diao , Gongyan Li , Shaoyun Xu , Yuexing Hao

Modern iterations of deep learning models contain millions (billions) of unique parameters, each represented by a b-bit number. Popular attempts at compressing neural networks (such as pruning and quantisation) have shown that many of the…

Machine Learning · Computer Science 2022-10-26 Christopher Subia-Waud , Srinandan Dasmahapatra

Tensor decomposition of convolutional and fully-connected layers is an effective way to reduce parameters and FLOP in neural networks. Due to memory and power consumption limitations of mobile or embedded devices, the quantization step is…

Machine Learning · Computer Science 2023-08-10 Daria Cherniuk , Stanislav Abukhovich , Anh-Huy Phan , Ivan Oseledets , Andrzej Cichocki , Julia Gusak

The 8 bits quantization has been widely applied to accelerate network inference in various deep learning applications. There are two kinds of quantization methods, training-based quantization and post-training quantization. Training-based…

Computer Vision and Pattern Recognition · Computer Science 2020-07-01 Di Wu , Qi Tang , Yongle Zhao , Ming Zhang , Ying Fu , Debing Zhang

Post-training quantization for reducing the storage of deep neural network models has been demonstrated to be an effective way in various tasks. However, low-bit quantization while maintaining model accuracy is a challenging problem. In…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Bingtao Yang , Yujia Wang , Mengzhi Jiao , Hongwei Huo

Post-training, layer-wise quantization is preferable because it is free from retraining and is hardware-friendly. Nevertheless, accuracy degradation has occurred when a neural network model has a big difference of per-out-channel weight…

Machine Learning · Computer Science 2020-08-14 Jihun Oh , SangJeong Lee , Meejeong Park , Pooni Walagaurav , Kiseok Kwon

Due to their large size, generative Large Language Models (LLMs) require significant computing and storage resources. This paper introduces a new post-training quantization method, GPTQT, to reduce memory usage and enhance processing speed…

Machine Learning · Computer Science 2024-07-04 Yipin Guo , Yilin Lang , Qinyuan Ren

Quantizing weights and activations of deep neural networks results in significant improvement in inference efficiency at the cost of lower accuracy. A source of the accuracy gap between full precision and quantized models is the…

Machine Learning · Computer Science 2020-06-16 Hadi Pouransari , Zhucheng Tu , Oncel Tuzel