English
Related papers

Related papers: Improving Neural Network Quantization without Retr…

200 papers

Quantization for deep neural networks (DNNs) is the process of mapping the parameter values of DNNs from original data types to other data types of lower precision to reduce model sizes and make inference faster. Quantization often maps…

Machine Learning · Computer Science 2025-02-07 Jaewoo Song , Fangzhen Lin

Outliers in weights and activations pose a key challenge for fixed-point quantization of neural networks. While they can be addressed by fine-tuning, this is not practical for ML service providers (e.g., Google or Microsoft) who often…

Machine Learning · Computer Science 2021-05-28 Ritchie Zhao , Jordan Dotzel , Zhanqiu Hu , Preslav Ivanov , Christopher De Sa , Zhiru Zhang

While 4-bit quantization is essential for high-throughput deployment of Large Language Models, activation outliers often lead to significant accuracy degradation due to the restricted dynamic range of low-bit formats. In this paper, we…

Machine Learning · Computer Science 2026-04-15 Zhiyuan Zhang , Yanzhao Li , Zhiqiang Zou , Bai Du , Yupeng Sun , Hui Dong , Hui Wang

Post-training quantization~(PTQ) of transformer language models faces significant challenges due to the existence of detrimental outliers in activations. We observe that these outliers are concentrated in specific channels and are…

Computation and Language · Computer Science 2023-10-24 Xiuying Wei , Yunchen Zhang , Yuhang Li , Xiangguo Zhang , Ruihao Gong , Jinyang Guo , Xianglong Liu

Lightweight design of Convolutional Neural Networks (CNNs) requires co-design efforts in the model architectures and compression techniques. As a novel design paradigm that separates training and inference, a structural re-parameterized…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Muqun Niu , Yuan Ren , Boyu Li , Chenchen Ding

Network quantization has emerged as one of the most practical model compression techniques, which significantly reduces a model's memory and compute consumption by mapping floating-point numbers to low-bit representations. However, existing…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Peilin Sun , Jianxin Wu

Transformer models have been widely adopted in various domains over the last years, and especially large language models have advanced the field of AI significantly. Due to their size, the capability of these networks has increased…

Machine Learning · Computer Science 2023-11-10 Yelysei Bondarenko , Markus Nagel , Tijmen Blankevoort

Outlier Features (OFs) are neurons whose activation magnitudes significantly exceed the average over a neural network's (NN) width. They are well known to emerge during standard transformer training and have the undesirable effect of…

Machine Learning · Computer Science 2024-11-08 Bobby He , Lorenzo Noci , Daniele Paliotta , Imanol Schlag , Thomas Hofmann

Quantization techniques, including quantization-aware training (QAT) and post-training quantization (PTQ), have become essential for inference acceleration of image super-resolution (SR) networks. Compared to QAT, PTQ has garnered…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Hailing Wang , jianglin Lu , Yitian Zhang , Yun Fu

Deep neural networks have achieved great success in classification tasks during the last years. However, one major problem to the path towards artificial intelligence is the inability of neural networks to accurately detect samples from…

Machine Learning · Computer Science 2021-03-16 Aristotelis-Angelos Papadopoulos , Mohammad Reza Rajati , Nazim Shaikh , Jiamian Wang

Diffusion models have achieved remarkable success in image generation but come with significant computational costs, posing challenges for deployment in resource-constrained environments. Recent post-training quantization (PTQ) methods have…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Dongyeun Lee , Jiwan Hur , Hyounguk Shon , Jae Young Lee , Junmo Kim

Convolutional Neural Networks (CNNs) have shown to be powerful medical image segmentation models. In this study, we address some of the main unresolved issues regarding these models. Specifically, training of these models on small medical…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Davood Karimi , Ali Gholipour

Channel pruning can significantly accelerate and compress deep neural networks. Many channel pruning works utilize structured sparsity regularization to zero out all the weights in some channels and automatically obtain structure-sparse…

Computer Vision and Pattern Recognition · Computer Science 2019-07-02 Jiashi Li , Qi Qi , Jingyu Wang , Ce Ge , Yujian Li , Zhangzhang Yue , Haifeng Sun

Out-of-distribution (OOD) detection and OOD generalization are widely studied in Deep Neural Networks (DNNs), yet their relationship remains poorly understood. We empirically show that the degree of Neural Collapse (NC) in a network layer…

Machine Learning · Computer Science 2025-09-23 Md Yousuf Harun , Jhair Gallardo , Christopher Kanan

Optimal transmission switching (OTS) improves optimal power flow (OPF) by selectively opening transmission lines, but its mixed-integer formulation increases computational complexity, especially on large grids. To address this, we propose a…

Systems and Control · Electrical Eng. & Systems 2026-03-05 Minsoo Kim , Matthew Brun , Andy Sun , Jip Kim

We consider the problem of accurate quantization for language models, where both the weights and activations are uniformly quantized to 4 bits per parameter, the lowest bitwidth format natively supported by GPU hardware. In this context,…

Machine Learning · Computer Science 2024-08-28 Aniruddha Nrusimha , Mayank Mishra , Naigang Wang , Dan Alistarh , Rameswar Panda , Yoon Kim

This paper aims at rapid deployment of the state-of-the-art deep neural networks (DNNs) to energy efficient accelerators without time-consuming fine tuning or the availability of the full datasets. Converting DNNs in full precision to…

Neural and Evolutionary Computing · Computer Science 2018-10-15 Jun Haeng Lee , Sangwon Ha , Saerom Choi , Won-Jo Lee , Seungwon Lee

In this paper, we study the OOD generalization of neural algorithmic reasoning tasks, where the goal is to learn an algorithm (e.g., sorting, breadth-first search, and depth-first search) from input-output pairs using deep neural networks.…

Machine Learning · Computer Science 2023-03-21 Sadegh Mahdavi , Kevin Swersky , Thomas Kipf , Milad Hashemi , Christos Thrampoulidis , Renjie Liao

The use of machine learning methods to tackle challenging physical layer signal processing tasks has attracted significant attention. In this work, we focus on the use of neural networks (NNs) to perform pilot-assisted channel estimation in…

Signal Processing · Electrical Eng. & Systems 2020-02-26 Michel van Lier , Alexios Balatsoukas-Stimming , Henk Corporaaal , Zoran Zivkovic

The accuracy of machine learning interatomic potentials suffers from reference data that contains numerical noise. Often originating from unconverged or inconsistent electronic-structure calculations, this noise is challenging to identify.…

Machine Learning · Statistics 2026-02-10 Terry C. W. Lam , Niamh O'Neill , Christoph Schran , Lars L. Schaaf
‹ Prev 1 2 3 10 Next ›