English
Related papers

Related papers: Training with Quantization Noise for Extreme Model…

200 papers

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

Neural network quantization and pruning are two techniques commonly used to reduce the computational complexity and memory footprint of these models for deployment. However, most existing pruning strategies operate on full-precision and…

Computer Vision and Pattern Recognition · Computer Science 2020-02-04 Luis Guerra , Bohan Zhuang , Ian Reid , Tom Drummond

A popular track of network compression approach is Quantization aware Training (QAT), which accelerates the forward pass during the neural network training and inference. However, not much prior efforts have been made to quantize and…

Computer Vision and Pattern Recognition · Computer Science 2023-11-02 Kaixin Xu , Alina Hui Xiu Lee , Ziyuan Zhao , Zhe Wang , Min Wu , Weisi Lin

This paper tackles the problem of training a deep convolutional neural network with both low-precision weights and low-bitwidth activations. Optimizing a low-precision network is very challenging since the training process can easily get…

Computer Vision and Pattern Recognition · Computer Science 2021-06-05 Bohan Zhuang , Chunhua Shen , Mingkui Tan , Lingqiao Liu , Ian Reid

Quantized neural networks can be viewed as a chain of noisy channels, where rounding in each layer reduces capacity as bit-width shrinks; the floating-point (FP) checkpoint sets the maximum input rate. We track capacity dynamics as the…

Machine Learning · Computer Science 2025-11-12 Sergey Salishev , Ian Akhremchik

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

Compressing neural nets is an active research problem, given the large size of state-of-the-art nets for tasks such as object recognition, and the computational limits imposed by mobile devices. We give a general formulation of model…

Machine Learning · Computer Science 2017-07-06 Miguel Á. Carreira-Perpiñán

Quantization lowers memory usage, computational requirements, and latency by utilizing fewer bits to represent model weights and activations. In this work, we investigate the generalization properties of quantized neural networks, a…

Although considerable progress has been obtained in neural network quantization for efficient inference, existing methods are not scalable to heterogeneous devices as one dedicated model needs to be trained, transmitted, and stored for one…

Machine Learning · Computer Science 2022-12-13 Hai Wu , Ruifei He , Haoru Tan , Xiaojuan Qi , Kaibin Huang

State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Low-bit neural network…

Computation and Language · Computer Science 2021-12-22 Junhao Xu , Jianwei Yu , Shoukang Hu , Xunying Liu , Helen Meng

Latent Diffusion Models (LDMs) capture the dynamic evolution of latent variables over time, blending patterns and multimodality in a generative system. Despite the proficiency of LDM in various applications, such as text-to-image…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Yuewei Yang , Xiaoliang Dai , Jialiang Wang , Peizhao Zhang , Hongbo Zhang

Supervised fine-tuning is a standard method for adapting pre-trained large language models (LLMs) to downstream tasks. Quantization has been recently studied as a post-training technique for efficient LLM deployment. To obtain quantized…

Machine Learning · Computer Science 2025-06-09 Quan Wei , Chung-Yiu Yau , Hoi-To Wai , Yang Katie Zhao , Dongyeop Kang , Youngsuk Park , Mingyi Hong

Quantization is a widely used technique to compress and accelerate deep neural networks. However, conventional quantization methods use the same bit-width for all (or most of) the layers, which often suffer significant accuracy degradation…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Weihan Chen , Peisong Wang , Jian Cheng

Quantization techniques can reduce the size of Deep Neural Networks and improve inference latency and throughput by taking advantage of high throughput integer instructions. In this paper we review the mathematical aspects of quantization…

Machine Learning · Computer Science 2020-04-22 Hao Wu , Patrick Judd , Xiaojie Zhang , Mikhail Isaev , Paulius Micikevicius

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

Although deep neural networks are highly effective, their high computational and memory costs severely challenge their applications on portable devices. As a consequence, low-bit quantization, which converts a full-precision neural network…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Jiwei Yang , Xu Shen , Jun Xing , Xinmei Tian , Houqiang Li , Bing Deng , Jianqiang Huang , Xiansheng Hua

Although deep learning models are highly effective for various learning tasks, their high computational costs prohibit the deployment to scenarios where either memory or computational resources are limited. In this paper, we focus on…

Computer Vision and Pattern Recognition · Computer Science 2017-09-14 Cong Leng , Hao Li , Shenghuo Zhu , Rong Jin

The size of a model has been a strong predictor of its quality, as well as its cost. As such, the trade-off between model cost and quality has been well-studied. Post-training optimizations like quantization and pruning have typically…

Machine Learning · Computer Science 2025-08-29 Giuseppe Franco , Pablo Monteagudo-Lago , Ian Colbert , Nicholas Fraser , Michaela Blott

Network quantization aims at reducing bit-widths of weights and/or activations, particularly important for implementing deep neural networks with limited hardware resources. Most methods use the straight-through estimator (STE) to train…

Computer Vision and Pattern Recognition · Computer Science 2021-04-05 Junghyup Lee , Dohyung Kim , Bumsub Ham

We analyze the effect of quantizing weights and activations of neural networks on their loss and derive a simple regularization scheme that improves robustness against post-training quantization. By training quantization-ready networks, our…

Machine Learning · Computer Science 2020-02-19 Milad Alizadeh , Arash Behboodi , Mart van Baalen , Christos Louizos , Tijmen Blankevoort , Max Welling