English
Related papers

Related papers: Reducing Storage of Pretrained Neural Networks by …

200 papers

This work focuses on reducing neural network size, which is a major driver of neural network execution time, power consumption, bandwidth, and memory footprint. A key challenge is to reduce size in a manner that can be exploited readily for…

Machine Learning · Computer Science 2025-06-18 Szabolcs Cséfalvay , James Imber

Compressing large neural networks is an important step for their deployment in resource-constrained computational platforms. In this context, vector quantization is an appealing framework that expresses multiple parameters using a single…

Computer Vision and Pattern Recognition · Computer Science 2021-04-13 Julieta Martinez , Jashan Shewakramani , Ting Wei Liu , Ioan Andrei Bârsan , Wenyuan Zeng , Raquel Urtasun

Large Language Models (LLMs) achieve strong performance across tasks, but face storage and compute challenges on edge devices. We propose EntroLLM, a compression framework combining mixed quantization and entropy coding to reduce storage…

Machine Learning · Computer Science 2026-05-05 Arnab Sanyal , Gourav Datta , Prithwish Mukherjee , Sandeep P. Chinchali , Michael Orshansky

With neural networks growing deeper and feature maps growing larger, limited communication bandwidth with external memory (or DRAM) and power constraints become a bottleneck in implementing network inference on mobile and edge devices. In…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Shanzhi Yin , Tongda Xu , Yongsheng Liang , Yuanyuan Wang , Yanghao Li , Yan Wang , Jingjing Liu

For neural video codec, it is critical, yet challenging, to design an efficient entropy model which can accurately predict the probability distribution of the quantized latent representation. However, most existing video codecs directly use…

Image and Video Processing · Electrical Eng. & Systems 2022-07-14 Jiahao Li , Bin Li , Yan Lu

Neural compression has brought tremendous progress in designing lossy compressors with good rate-distortion (RD) performance at low complexity. Thus far, neural compression design involves transforming the source to a latent vector, which…

Information Theory · Computer Science 2025-07-15 Eric Lei , Hamed Hassani , Shirin Saeedi Bidokhti

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

Neural image compression has been shown to outperform traditional image codecs in terms of rate-distortion performance. However, quantization introduces errors in the compression process, which can degrade the quality of the compressed…

Machine Learning · Computer Science 2024-03-27 Wei Luo , Bo Chen

This paper presents a set of full-resolution lossy image compression methods based on neural networks. Each of the architectures we describe can provide variable compression rates during deployment without requiring retraining of the…

Computer Vision and Pattern Recognition · Computer Science 2017-07-10 George Toderici , Damien Vincent , Nick Johnston , Sung Jin Hwang , David Minnen , Joel Shor , Michele Covell

Relative entropy coding (REC) algorithms encode a random sample following a target distribution $Q$, using a coding distribution $P$ shared between the sender and receiver. Sadly, general REC algorithms suffer from prohibitive encoding…

Information Theory · Computer Science 2024-10-30 Jiajun He , Gergely Flamich , José Miguel Hernández-Lobato

We tackle the problem of producing compact models, maximizing their accuracy for a given model size. A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the…

Machine Learning · Computer Science 2021-03-02 Angela Fan , Pierre Stock , Benjamin Graham , Edouard Grave , Remi Gribonval , Herve Jegou , Armand Joulin

Neural receivers have shown outstanding performance compared to the conventional ones but this comes with a high network complexity leading to a heavy computational cost. This poses significant challenges in their deployment on…

Information Theory · Computer Science 2025-11-05 Roberta Fiandaca , Manil Dev Gomony

Model compression has gained a lot of attention due to its ability to reduce hardware resource requirements significantly while maintaining accuracy of DNNs. Model compression is especially useful for memory-intensive recurrent neural…

Machine Learning · Computer Science 2018-05-30 Dongsoo Lee , Byeongwook Kim

Despite their high accuracy, complex neural networks demand significant computational resources, posing challenges for deployment on resource constrained devices such as mobile phones and embedded systems. Compression algorithms have been…

Machine Learning · Computer Science 2025-09-23 Ali Aghababaei-Harandi , Massih-Reza Amini

The performance of neural networks improves when more parameters are used. However, the model sizes are constrained by the available on-device memory during training and inference. Although applying techniques like quantization can…

Machine Learning · Computer Science 2024-10-29 Yongchang Hao , Yanshuai Cao , Lili Mou

Despite the success of CNN models on a variety of Image classification and segmentation tasks, their extensive computational and storage demands pose considerable challenges for real-world deployment on resource-constrained devices.…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Ahmed Luqman , Khuzemah Qazi , Murray Patterson , Malik Jahan Khan , Imdadullah Khan

We propose a general framework for neural network compression that is motivated by the Minimum Description Length (MDL) principle. For that we first derive an expression for the entropy of a neural network, which measures its complexity…

Machine Learning · Computer Science 2018-12-20 Simon Wiedemann , Arturo Marban , Klaus-Robert Müller , Wojciech Samek

Network quantization is one of network compression techniques to reduce the redundancy of deep neural networks. It reduces the number of distinct network parameter values by quantization in order to save the storage for them. In this paper,…

Computer Vision and Pattern Recognition · Computer Science 2017-11-15 Yoojin Choi , Mostafa El-Khamy , Jungwon Lee

Despite the growing availability of high-capacity computational platforms, implementation complexity still has been a great concern for the real-world deployment of neural networks. This concern is not exclusively due to the huge costs of…

Machine Learning · Computer Science 2023-12-19 Felipe Dennis de Resende Oliveira , Eduardo Luiz Ortiz Batista , Rui Seara

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