English
Related papers

Related papers: Activation Density based Mixed-Precision Quantizat…

200 papers

Quantization is a technique for reducing deep neural networks (DNNs) training and inference times, which is crucial for training in resource constrained environments or applications where inference is time critical. State-of-the-art (SOTA)…

Machine Learning · Computer Science 2023-05-24 Lorenz Kummer , Kevin Sidak , Tabea Reichmann , Wilfried Gansterer

Deep learning as a means to inferencing has proliferated thanks to its versatility and ability to approach or exceed human-level accuracy. These computational models have seemingly insatiable appetites for computational resources not only…

This paper addresses a challenging problem - how to reduce energy consumption without incurring performance drop when deploying deep neural networks (DNNs) at the inference stage. In order to alleviate the computation and storage burdens,…

Machine Learning · Computer Science 2019-01-09 Xue Geng , Jie Fu , Bin Zhao , Jie Lin , Mohamed M. Sabry Aly , Christopher Pal , Vijay Chandrasekhar

Quantization of the weights and activations is one of the main methods to reduce the computational footprint of Deep Neural Networks (DNNs) training. Current methods enable 4-bit quantization of the forward phase. However, this constitutes…

Machine Learning · Computer Science 2024-06-11 Brian Chmiel , Ron Banner , Elad Hoffer , Hilla Ben Yaacov , Daniel Soudry

Mixed-precision Deep Neural Networks achieve the energy efficiency and throughput needed for hardware deployment, particularly when the resources are limited, without sacrificing accuracy. However, the optimal per-layer bit precision that…

Machine Learning · Computer Science 2022-08-15 Mariam Rakka , Mohammed E. Fouda , Pramod Khargonekar , Fadi Kurdahi

Although the quest for more accurate solutions is pushing deep learning research towards larger and more complex algorithms, edge devices demand efficient inference and therefore reduction in model size, latency and energy consumption. One…

Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…

Machine Learning · Computer Science 2022-10-14 Zheng Wang , Juncheng B Li , Shuhui Qu , Florian Metze , Emma Strubell

Deep networks run with low precision operations at inference time offer power and space advantages over high precision alternatives, but need to overcome the challenge of maintaining high accuracy as precision decreases. Here, we present a…

Machine Learning · Computer Science 2020-05-08 Steven K. Esser , Jeffrey L. McKinstry , Deepika Bablani , Rathinakumar Appuswamy , Dharmendra S. Modha

Deep Learning is moving to edge devices, ushering in a new age of distributed Artificial Intelligence (AI). The high demand of computational resources required by deep neural networks may be alleviated by approximate computing techniques,…

Neural and Evolutionary Computing · Computer Science 2018-11-15 Miguel de Prado , Maurizio Denna , Luca Benini , Nuria Pazos

Weight pruning and weight quantization are two important categories of DNN model compression. Prior work on these techniques are mainly based on heuristics. A recent work developed a systematic frame-work of DNN weight pruning using the…

Neural and Evolutionary Computing · Computer Science 2019-04-02 Shaokai Ye , Xiaoyu Feng , Tianyun Zhang , Xiaolong Ma , Sheng Lin , Zhengang Li , Kaidi Xu , Wujie Wen , Sijia Liu , Jian Tang , Makan Fardad , Xue Lin , Yongpan Liu , Yanzhi Wang

Model quantization reduces neural network parameter precision to achieve compression, but often compromises accuracy. Existing post-training quantization (PTQ) methods employ iterative parameter updates to preserve accuracy under high…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Zekang Zheng , Haokun Li , Yaofo Chen , Mingkui Tan , Qing Du

Quantization-aware training (QAT) is a leading technique for improving the accuracy of quantized neural networks. Previous work has shown that decomposing training into a full-precision (FP) phase followed by a QAT phase yields superior…

Machine Learning · Computer Science 2026-02-27 Aleksandr Dremov , David Grangier , Angelos Katharopoulos , Awni Hannun

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

Quantization of Deep Neural Network (DNN) activations is a commonly used technique to reduce compute and memory demands during DNN inference, which can be particularly beneficial on resource-constrained devices. To achieve high accuracy,…

Machine Learning · Computer Science 2024-12-16 Wenhao Hu , Paul Henderson , José Cano

In the era of large language models (LLMs), weight-activation quantization helps fit models on edge device by reducing memory and compute bit-widths. However, three challenges persist for energy constrained hardware: (1) even after…

Machine Learning · Computer Science 2025-10-23 Chenyu Wang , Zhanglu Yan , Zhi Zhou , Xu Chen , Weng-Fai Wong

Deep Neural Networks reached state-of-the-art performance across numerous domains, but this progress has come at the cost of increasingly large and over-parameterized models, posing serious challenges for deployment on resource-constrained…

Machine Learning · Computer Science 2026-02-04 Dario Malchiodi , Mattia Ferraretto , Marco Frasca

Efficient machine learning implementations optimized for inference in hardware have wide-ranging benefits, depending on the application, from lower inference latency to higher data throughput and reduced energy consumption. Two popular…

Machine Learning · Computer Science 2021-07-21 Benjamin Hawks , Javier Duarte , Nicholas J. Fraser , Alessandro Pappalardo , Nhan Tran , Yaman Umuroglu

State-space models (SSMs) have recently gained attention in deep learning for their ability to efficiently model long-range dependencies, making them promising candidates for edge-AI applications. In this paper, we analyze the effects of…

Machine Learning · Computer Science 2025-06-17 Leo Zhao , Tristan Torchet , Melika Payvand , Laura Kriener , Filippo Moro

In the traditional deep compression framework, iteratively performing network pruning and quantization can reduce the model size and computation cost to meet the deployment requirements. However, such a step-wise application of pruning and…

Computer Vision and Pattern Recognition · Computer Science 2020-11-13 Wenting Tang , Xingxing Wei , Bo Li

In this work, we developed and tested 3 techniques for vector quantization (VQ) based model weight compression. To mitigate codebook collapse and enable end-to-end training, we adopted cosine similarity-based assignment. Building on ideas…

Machine Learning · Computer Science 2026-04-28 Terry Gou , Puneet Gupta