English
Related papers

Related papers: Arithmetic-Intensity-Aware Quantization

200 papers

Quantization replaces floating point arithmetic with integer arithmetic in deep neural network models, providing more efficient on-device inference with less power and memory. In this work, we propose a framework for formally verifying…

Machine Learning · Computer Science 2023-12-29 Pei Huang , Haoze Wu , Yuting Yang , Ieva Daukantas , Min Wu , Yedi Zhang , Clark Barrett

Neural network quantization is a promising compression technique to reduce memory footprint and save energy consumption, potentially leading to real-time inference. However, there is a performance gap between quantized and full-precision…

Computer Vision and Pattern Recognition · Computer Science 2022-02-11 Qing Jin , Jian Ren , Richard Zhuang , Sumant Hanumante , Zhengang Li , Zhiyu Chen , Yanzhi Wang , Kaiyuan Yang , Sergey Tulyakov

Processing-in-memory (PIM), an increasingly studied neuromorphic hardware, promises orders of energy and throughput improvements for deep learning inference. Leveraging the massively parallel and efficient analog computing inside memories,…

Machine Learning · Computer Science 2022-09-20 Qing Jin , Zhiyu Chen , Jian Ren , Yanyu Li , Yanzhi Wang , Kaiyuan Yang

Quantizing neural networks is one of the most effective methods for achieving efficient inference on mobile and embedded devices. In particular, mixed precision quantized (MPQ) networks, whose layers can be quantized to different bitwidths,…

Machine Learning · Computer Science 2023-07-11 Jorn Peters , Marios Fournarakis , Markus Nagel , Mart van Baalen , Tijmen Blankevoort

Low-bit quantization emerges as one of the most promising compression approaches for deploying deep neural networks on edge devices. Mixed-precision quantization leverages a mixture of bit-widths to unleash the accuracy and efficiency…

Machine Learning · Computer Science 2024-05-24 Wei Huang , Haotong Qin , Yangdong Liu , Jingzhuo Liang , Yulun Zhang , Ying Li , Xianglong Liu

Graph neural networks (GNNs) have demonstrated strong performance on a wide variety of tasks due to their ability to model non-uniform structured data. Despite their promise, there exists little research exploring methods to make them more…

Machine Learning · Computer Science 2021-03-16 Shyam A. Tailor , Javier Fernandez-Marques , Nicholas D. Lane

Neural network quantization is frequently used to optimize model size, latency and power consumption for on-device deployment of neural networks. In many cases, a target bit-width is set for an entire network, meaning every layer get…

Machine Learning · Computer Science 2023-02-13 Nilesh Prasad Pandey , Markus Nagel , Mart van Baalen , Yin Huang , Chirag Patel , Tijmen Blankevoort

Model size and inference speed/power have become a major challenge in the deployment of Neural Networks for many applications. A promising approach to address these problems is quantization. However, uniformly quantizing a model to ultra…

Computer Vision and Pattern Recognition · Computer Science 2020-03-29 Zhen Dong , Zhewei Yao , Amir Gholami , Michael Mahoney , Kurt Keutzer

Network quantization is an effective method for the deployment of neural networks on memory and energy constrained mobile devices. In this paper, we propose a Dynamic Network Quantization (DNQ) framework which is composed of two modules: a…

Machine Learning · Computer Science 2018-12-07 Yuhui Xu , Shuai Zhang , Yingyong Qi , Jiaxian Guo , Weiyao Lin , Hongkai Xiong

Current low-precision quantization algorithms often have the hidden cost of conversion back and forth from floating point to quantized integer values. This hidden cost limits the latency improvement realized by quantizing Neural Networks.…

Computer Vision and Pattern Recognition · Computer Science 2021-06-24 Zhewei Yao , Zhen Dong , Zhangcheng Zheng , Amir Gholami , Jiali Yu , Eric Tan , Leyuan Wang , Qijing Huang , Yida Wang , Michael W. Mahoney , Kurt Keutzer

Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks, and thus, have been widely investigated. However, it lacks a systematic method to determine the…

Machine Learning · Computer Science 2021-02-23 Huanrui Yang , Lin Duan , Yiran Chen , Hai Li

INT8 quantization has become one of the standard techniques for deploying convolutional neural networks (CNNs) on edge devices to reduce the memory and computational resource usages. By analyzing quantized performances of existing…

Machine Learning · Computer Science 2020-12-01 Taehoon Kim , YoungJoon Yoo , Jihoon Yang

The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. We propose a quantization scheme that allows inference to be…

Machine Learning · Computer Science 2017-12-19 Benoit Jacob , Skirmantas Kligys , Bo Chen , Menglong Zhu , Matthew Tang , Andrew Howard , Hartwig Adam , Dmitry Kalenichenko

Network quantization is a dominant paradigm of model compression. However, the abrupt changes in quantized weights during training often lead to severe loss fluctuations and result in a sharp loss landscape, making the gradients unstable…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Jing Liu , Jianfei Cai , Bohan Zhuang

The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails to adapt to their varying complexity. Dynamic,…

Machine Learning · Computer Science 2026-03-24 Hazem Hesham Yousef Shalby , Fabrizio Pittorino , Francesca Palermo , Diana Trojaniello , Manuel Roveri

Integer AI inference significantly reduces computational complexity in embedded systems. Quantization-aware training (QAT) helps mitigate accuracy degradation associated with post-training quantization but still overlooks the impact of…

Machine Learning · Computer Science 2025-10-14 Lion Mueller , Alberto Garcia-Ortiz , Ardalan Najafi , Adam Fuks , Lennart Bamberg

Existing neural networks are memory-consuming and computationally intensive, making deploying them challenging in resource-constrained environments. However, there are various methods to improve their efficiency. Two such methods are…

Machine Learning · Computer Science 2023-11-10 Anastasiia Prutianova , Alexey Zaytsev , Chung-Kuei Lee , Fengyu Sun , Ivan Koryakovskiy

Quantization is a key method for reducing the GPU memory requirement of training large language models (LLMs). Yet, current approaches are ineffective for 4-bit activations and 8-bit gradients, which would easily cause slow convergence or…

Computation and Language · Computer Science 2026-05-12 Wenxiang Lin , Juntao Huang , Luhan Zhang , Laili Li , Xiang Bao , Mengyang Zhang , Bing Wang , Shaohuai Shi

The recent advent of `Internet of Things' (IOT) has increased the demand for enabling AI-based edge computing. This has necessitated the search for efficient implementations of neural networks in terms of both computations and storage.…

Machine Learning · Computer Science 2019-02-04 Indranil Chakraborty , Deboleena Roy , Aayush Ankit , Kaushik Roy

Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or…

Computer Vision and Pattern Recognition · Computer Science 2018-07-03 Julian Faraone , Nicholas Fraser , Michaela Blott , Philip H. W. Leong