English
Related papers

Related papers: Float8@2bits: Entropy Coding Enables Data-Free Mod…

200 papers

We propose in this paper a new paradigm for facial video compression. We leverage the generative capacity of GANs such as StyleGAN to represent and compress a video, including intra and inter compression. Each frame is inverted in the…

Image and Video Processing · Electrical Eng. & Systems 2022-07-14 Mustafa Shukor , Bharath Bhushan Damodaran , Xu Yao , Pierre Hellier

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

Recently, an extensive amount of research has been focused on compressing and accelerating Deep Neural Networks (DNN). So far, high compression rate algorithms require part of the training dataset for a low precision calibration, or a…

Machine Learning · Computer Science 2020-04-08 Matan Haroush , Itay Hubara , Elad Hoffer , Daniel Soudry

Language prediction is constrained by informational entropy intrinsic to language, such that there exists a limit to how accurate any language model can become and equivalently a lower bound to language compression. The most efficient…

Computation and Language · Computer Science 2025-11-14 Benjamin L. Badger , Matthew Neligeorge

End-to-end image/video codecs are getting competitive compared to traditional compression techniques that have been developed through decades of manual engineering efforts. These trainable codecs have many advantages over traditional…

Image and Video Processing · Electrical Eng. & Systems 2023-08-03 Muhammet Balcilar , Bharath Bhushan Damodaran , Karam Naser , Franck Galpin , Pierre Hellier

Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings. Despite their effectiveness, the number of parameters in an embedding layer increases linearly with the…

Machine Learning · Computer Science 2020-06-29 Ting Chen , Lala Li , Yizhou Sun

Contemporary lossy image and video coding standards rely on transform coding, the process through which pixels are mapped to an alternative representation to facilitate efficient data compression. Despite impressive performance of…

Image and Video Processing · Electrical Eng. & Systems 2023-02-21 Lyndon R. Duong , Bohan Li , Cheng Chen , Jingning Han

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks. However, their extensive memory requirements, particularly due to KV cache growth during long-text understanding and…

Computation and Language · Computer Science 2025-10-14 Haoqi Yang , Yao Yao , Zuchao Li , Baoyuan Qi , Guoming Liu , Hai Zhao

Large language models (LLMs) require substantial compute, and thus energy, at inference time. While quantizing weights and activations is effective at improving efficiency, naive quantization of LLMs can significantly degrade performance…

Machine Learning · Computer Science 2025-06-06 Boris van Breugel , Yelysei Bondarenko , Paul Whatmough , Markus Nagel

Deep neural networks have achieved state-of-the-art results in a wide range of applications, from natural language processing and computer vision to speech recognition. However, as tasks become increasingly complex, model sizes continue to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Tomer Gafni , Asaf Karnieli , Yair Hanani

In the wake of the success of convolutional neural networks in image classification, object recognition, speech recognition, etc., the demand for deploying these compute-intensive ML models on embedded and mobile systems with tight power…

Computer Vision and Pattern Recognition · Computer Science 2019-11-12 Lukas Cavigelli , Georg Rutishauser , Luca Benini

Video compression systems must support increasing bandwidth and data throughput at low cost and power, and can be limited by entropy coding bottlenecks. Efficiency can be greatly improved by parallelizing coding, which can be done at much…

Image and Video Processing · Electrical Eng. & Systems 2023-12-05 Amir Said , Hoang Le , Farzad Farhadzadeh

We introduce a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection. It achieves near-original model performance on common computer vision architectures and tasks. 8-bit…

Machine Learning · Computer Science 2019-11-26 Markus Nagel , Mart van Baalen , Tijmen Blankevoort , Max Welling

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

Neural network (NN) compression via techniques such as pruning, quantization requires setting compression hyperparameters (e.g., number of channels to be pruned, bitwidths for quantization) for each layer either manually or via neural…

Machine Learning · Computer Science 2023-06-14 Anshul Nasery , Hardik Shah , Arun Sai Suggala , Prateek Jain

Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computational overhead for inference. Existing CoT compression methods often suffer from a critical…

Machine Learning · Computer Science 2026-05-26 Yuntian Tang , Bohan Jia , Wenxuan Huang , Lianyue Zhang , Jiao Xie , Wenxi Li , Wei Li , Jie Hu , Xinghao Chen Rongrong Ji , Shaohui Lin

Modern scientific simulations generate massive volumes of data, creating significant challenges for I/O and storage systems. Error-bounded lossy compression (EBLC) offers a solution by reducing data set sizes while preserving data quality…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-16 Grant Wilkins , Sheng Di , Jon C. Calhoun , Robert Underwood , Franck Cappello

Multi-bit quantization networks enable flexible deployment of deep neural networks by supporting multiple precision levels within a single model. However, existing approaches suffer from significant training overhead as full-dataset updates…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Jinhee Kim , Jae Jun An , Kang Eun Jeon , Jong Hwan Ko

Model compression is vital to the deployment of deep learning on edge devices. Low precision representations, achieved via quantization of weights and activations, can reduce inference time and memory requirements. However, quantifying and…

Machine Learning · Computer Science 2022-10-18 Ben Zandonati , Adrian Alan Pol , Maurizio Pierini , Olya Sirkin , Tal Kopetz

We formulate the entropy of a quantized artificial neural network as a differentiable function that can be plugged as a regularization term into the cost function minimized by gradient descent. Our formulation scales efficiently beyond the…

Machine Learning · Computer Science 2021-07-13 Enzo Tartaglione , Stéphane Lathuilière , Attilio Fiandrotti , Marco Cagnazzo , Marco Grangetto