English
Related papers

Related papers: Soft Quantization: Model Compression Via Weight Co…

200 papers

Compression of Neural Networks (NN) has become a highly studied topic in recent years. The main reason for this is the demand for industrial scale usage of NNs such as deploying them on mobile devices, storing them efficiently, transmitting…

Machine Learning · Statistics 2017-12-08 Marco Federici , Karen Ullrich , Max Welling

In this paper, we introduce a novel method of neural network weight compression. In our method, we store weight tensors as sparse, quantized matrix factors, whose product is computed on the fly during inference to generate the target…

Machine Learning · Computer Science 2022-07-25 Andrey Kuzmin , Mart van Baalen , Markus Nagel , Arash Behboodi

Post-training quantization (PTQ) is a neural network compression technique that converts a full-precision model into a quantized model using lower-precision data types. Although it can help reduce the size and computational cost of deep…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Jiawei Liu , Lin Niu , Zhihang Yuan , Dawei Yang , Xinggang Wang , Wenyu Liu

The quantization of large language models (LLMs) has been a prominent research area aimed at enabling their lightweight deployment in practice. Existing research about LLM's quantization has mainly explored the interplay between weights and…

Computation and Language · Computer Science 2025-05-16 Yifei Gao , Jie Ou , Lei Wang , Jun Cheng , Mengchu Zhou

Deep learning models have achieved tremendous success in most of the industries in recent years. The evolution of these models has also led to an increase in the model size and energy requirement, making it difficult to deploy in production…

Machine Learning · Computer Science 2024-07-24 Aayush Saxena , Arit Kumar Bishwas , Ayush Ashok Mishra , Ryan Armstrong

Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models are held in memory. Model compression methods address this…

Post-training quantization is widely employed to reduce the computational demands of neural networks. Typically, individual substructures, such as layers or blocks of layers, are quantized with the objective of minimizing quantization…

Machine Learning · Computer Science 2024-11-07 Khasmamad Shabanovi , Lukas Wiest , Vladimir Golkov , Daniel Cremers , Thomas Pfeil

The rising performance of deep neural networks is often empirically attributed to an increase in the available computational power, which allows complex models to be trained upon large amounts of annotated data. However, increased model…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Gauthier Tallec , Edouard Yvinec , Arnaud Dapogny , Kevin Bailly

Neural networks have shown great performance in cognitive tasks. When deploying network models on mobile devices with limited resources, weight quantization has been widely adopted. Binary quantization obtains the highest compression but…

Computer Vision and Pattern Recognition · Computer Science 2018-11-14 Hsin-Pai Cheng , Yuanjun Huang , Xuyang Guo , Yifei Huang , Feng Yan , Hai Li , Yiran Chen

In this article, we introduce a novel normalization technique for neural network weight matrices, which we term weight conditioning. This approach aims to narrow the gap between the smallest and largest singular values of the weight…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Hemanth Saratchandran , Thomas X. Wang , Simon Lucey

Quantization based model compression serves as high performing and fast approach for inference that yields models which are highly compressed when compared to their full-precision floating point counterparts. The most extreme quantization…

Machine Learning · Computer Science 2021-11-09 Yaniv Shulman

Machine unlearning, as a post-hoc processing technique, has gained widespread adoption in addressing challenges like bias mitigation and robustness enhancement, colloquially, machine unlearning for fairness and robustness. However, existing…

Machine Learning · Computer Science 2025-05-27 Xinbao Qiao , Ningning Ding , Yushi Cheng , Meng Zhang

We propose DiffQ a differentiable method for model compression for quantizing model parameters without gradient approximations (e.g., Straight Through Estimator). We suggest adding independent pseudo quantization noise to model parameters…

Machine Learning · Statistics 2022-10-18 Alexandre Défossez , Yossi Adi , Gabriel Synnaeve

Deep networks are typically trained with many more parameters than the size of the training dataset. Recent empirical evidence indicates that the practice of overparameterization not only benefits training large models, but also assists -…

Machine Learning · Computer Science 2020-12-17 Xiangyu Chang , Yingcong Li , Samet Oymak , Christos Thrampoulidis

Deep Neural Networks (DNNs) have achieved significant advances in a wide range of applications. However, their deployment on resource-constrained devices remains a challenge due to the large number of layers and parameters, which result in…

Neural and Evolutionary Computing · Computer Science 2025-09-05 Sara Makenali , Babak Rokh , Ali Azarpeyvand

Optimal decision making requires that classifiers produce uncertainty estimates consistent with their empirical accuracy. However, deep neural networks are often under- or over-confident in their predictions. Consequently, methods have been…

The state-of-the-art performance for several real-world problems is currently reached by convolutional neural networks (CNN). Such learning models exploit recent results in the field of deep learning, typically leading to highly performing,…

Machine Learning · Computer Science 2021-08-31 Giosuè Cataldo Marinò , Alessandro Petrini , Dario Malchiodi , Marco Frasca

Thanks to their state-of-the-art performance, deep neural networks are increasingly used for object recognition. To achieve these results, they use millions of parameters to be trained. However, when targeting embedded applications the size…

Machine Learning · Computer Science 2016-03-21 Guillaume Soulié , Vincent Gripon , Maëlys Robert

Large language models of high parameter counts are computationally expensive, yet can be made much more efficient by compressing their weights to very low numerical precision. This can be achieved either through post-training quantization…

Machine Learning · Computer Science 2025-04-21 Zifei Xu , Sayeh Sharify , Wanzin Yazar , Tristan Webb , Xin Wang

Deep Learning models have become the dominant approach in several areas due to their high performance. Unfortunately, the size and hence computational requirements of operating such models can be considerably high. Therefore, this…

Computer Vision and Pattern Recognition · Computer Science 2019-12-04 Abdullah Salama , Oleksiy Ostapenko , Tassilo Klein , Moin Nabi