English
Related papers

Related papers: Lossy and Lossless (L$^2$) Post-training Model Siz…

200 papers

Generalization abilities of well-trained large language models (LLMs) are known to scale predictably as a function of model size. In contrast to the existence of practical scaling laws governing pre-training, the quality of LLMs after…

Machine Learning · Computer Science 2024-12-09 Zifei Xu , Alexander Lan , Wanzin Yazar , Tristan Webb , Sayeh Sharify , Xin Wang

The ever-growing size of neural networks poses serious challenges on resource-constrained devices, such as embedded sensors. Compression algorithms that reduce their size can mitigate these problems, provided that model performance stays…

Machine Learning · Computer Science 2025-05-27 Alexander Conzelmann , Robert Bamler

Due to the fundamental connection between next-symbol prediction and compression, modern predictive models, such as large language models (LLMs), can be combined with entropy coding to achieve compression rates that surpass those of…

Information Theory · Computer Science 2026-01-27 Cordelia Hu , Jennifer Tang

Large-scale scientific simulations generate massive datasets, posing challenges for storage and I/O. Traditional lossy compression struggles to advance more in balancing compression ratio, data quality, and adaptability to diverse…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-21 Wenqi Jia , Zhewen Hu , Youyuan Liu , Boyuan Zhang , Jinzhen Wang , Jinyang Liu , Wei Niu , Stavros Kalafatis , Junzhou Huang , Sian Jin , Daoce Wang , Jiannan Tian , Miao Yin

Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased latency at inference. We propose a novel model compression…

Machine Learning · Computer Science 2020-06-15 Tao Lin , Sebastian U. Stich , Luis Barba , Daniil Dmitriev , Martin Jaggi

As deep neural networks (DNNs) grow in complexity and size, the resultant increase in communication overhead during distributed training has become a significant bottleneck, challenging the scalability of distributed training systems.…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-02-13 Haoyu Li , Yuchen Xu , Jiayi Chen , Rohit Dwivedula , Wenfei Wu , Keqiang He , Aditya Akella , Daehyeok Kim

This paper proposes \textit{layer fusion} - a model compression technique that discovers which weights to combine and then fuses weights of similar fully-connected, convolutional and attention layers. Layer fusion can significantly reduce…

Machine Learning · Computer Science 2020-07-30 James O' Neill , Greg Ver Steeg , Aram Galstyan

During the training of Large Language Models (LLMs), tensor data is periodically "checkpointed" to persistent storage to allow recovery of work done in the event of failure. The volume of data that must be copied during each checkpoint,…

Machine Learning · Computer Science 2025-05-16 Daniel Waddington , Cornel Constantinescu

While large language models (LLMs) have achieved remarkable performance across a wide range of tasks, their massive scale incurs prohibitive computational and memory costs for pre-training from scratch. Recent studies have investigated the…

Machine Learning · Computer Science 2025-08-05 Jiaxi Li , Lu Yin , Li Shen , Jinjin Xu , Liwu Xu , Tianjin Huang , Wenwu Wang , Shiwei Liu , Xilu Wang

Scaling models has led to significant advancements in deep learning, but training these models in decentralized settings remains challenging due to communication bottlenecks. While existing compression techniques are effective in…

Machine Learning · Computer Science 2025-06-03 Sameera Ramasinghe , Thalaiyasingam Ajanthan , Gil Avraham , Yan Zuo , Alexander Long

Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…

Computation and Language · Computer Science 2026-04-17 Andrew Kiruluta

As deep learning models grow and deployment becomes more widespread, reducing the storage and transmission costs of neural network weights has become increasingly important. While prior work such as ZipNN has shown that lossless compression…

Machine Learning · Computer Science 2025-08-28 Anat Heilper , Doron Singer

State-of-the-art deep learning models have a parameter count that reaches into the billions. Training, storing and transferring such models is energy and time consuming, thus costly. A big part of these costs is caused by training the…

Machine Learning · Computer Science 2023-05-26 Paul Wimmer , Jens Mehnert , Alexandru Paul Condurache

Lossless and near-lossless image compression is of paramount importance to professional users in many technical fields, such as medicine, remote sensing, precision engineering and scientific research. But despite rapidly growing research…

Image and Video Processing · Electrical Eng. & Systems 2024-01-12 Yuanchao Bai , Xianming Liu , Kai Wang , Xiangyang Ji , Xiaolin Wu , Wen Gao

With the development of foundational models, model compression has become a critical requirement. Various model compression approaches have been proposed such as low-rank decomposition, pruning, quantization, ergodic dynamic systems, and…

Machine Learning · Computer Science 2026-04-01 Jing-Xiao Liao , Haoran Wang , Tao Li , Daoming Lyu , Yi Zhang , Chengjun Cai , Feng-Lei Fan

Large Language Models (LLMs) have shown impressive capabilities across diverse tasks, but their large memory and compute demands hinder deployment. Ternarization has gained attention as a promising compression technique, delivering…

Machine Learning · Computer Science 2026-02-02 Xianglong Yan , Chengzhu Bao , Zhiteng Li , Tianao Zhang , Kaicheng Yang , Haotong Qin , Ruobing Xie , Xingwu Sun , Yulun Zhang

Ensemble methods are among the state-of-the-art predictive modeling approaches. Applied to modern big data, these methods often require a large number of sub-learners, where the complexity of each learner typically grows with the size of…

Machine Learning · Computer Science 2018-10-29 Amichai Painsky , Saharon Rosset

We introduce model folding, a novel data-free model compression technique that merges structurally similar neurons across layers, significantly reducing the model size without the need for fine-tuning or access to training data. Unlike…

Machine Learning · Computer Science 2025-08-13 Dong Wang , Haris Šikić , Lothar Thiele , Olga Saukh

Deploying deep learning models, comprising of non-linear combination of millions, even billions, of parameters is challenging given the memory, power and compute constraints of the real world. This situation has led to research into model…

Machine Learning · Computer Science 2020-05-29 Muhammad A. Shah , Raphael Olivier , Bhiksha Raj

Model compression has been introduced to reduce the required hardware resources while maintaining the model accuracy. Lots of techniques for model compression, such as pruning, quantization, and low-rank approximation, have been suggested…

Machine Learning · Computer Science 2018-10-31 Dongsoo Lee , Parichay Kapoor , Byeongwook Kim