English
Related papers

Related papers: Practical Lossless Compression with Latent Variabl…

200 papers

Understanding the coordinated activity underlying brain computations requires large-scale, simultaneous recordings from distributed neuronal structures at a cellular-level resolution. One major hurdle to design high-bandwidth,…

Neural and Evolutionary Computing · Computer Science 2018-09-18 Tong Wu , Wenfeng Zhao , Edward Keefer , Zhi Yang

A new Lossy Causal Temporal Convolutional Neural Network Autoencoder for anomaly detection is proposed in this work. Our framework uses a rate-distortion loss and an entropy bottleneck to learn a compressed latent representation for the…

Machine Learning · Computer Science 2022-12-06 Christopher P. Ley , Jorge F. Silva

Recent AI applications such as Collaborative Intelligence with neural networks involve transferring deep feature tensors between various computing devices. This necessitates tensor compression in order to optimize the usage of…

Machine Learning · Computer Science 2020-02-18 Hyomin Choi , Robert A. Cohen , Ivan V. Bajic

Models with a large number of latent variables are often used to fully utilize the information in big or complex data. However, they can be difficult to estimate using standard approaches, and variational inference methods are a popular…

Methodology · Statistics 2021-04-20 Rubén Loaiza-Maya , Michael Stanley Smith , David J. Nott , Peter J. Danaher

Approximate nearest neighbor search for vectors relies on indexes that are most often accessed from RAM. Therefore, storage is the factor limiting the size of the database that can be served from a machine. Lossy vector compression, i.e.,…

Machine Learning · Computer Science 2025-01-22 Daniel Severo , Giuseppe Ottaviano , Matthew Muckley , Karen Ullrich , Matthijs Douze

Existing work on prompt compression for Large Language Models (LLM) focuses on lossy methods that try to maximize the retention of semantic information that is relevant to downstream tasks while significantly reducing the sequence length.…

Computation and Language · Computer Science 2025-08-22 John Harvill , Ziwei Fan , Hao Wang , Luke Huan , Anoop Deoras , Yizhou Sun , Hao Ding

Among other uses, neural networks are a powerful tool for solving deterministic and Bayesian inverse problems in real-time, where variational autoencoders, a specialized type of neural network, enable the Bayesian estimation of model…

Machine Learning · Computer Science 2025-09-25 Andrea Tonini , Luca Dede'

Backward propagation (BP) is widely used to compute the gradients in neural network training. However, it is hard to implement BP on edge devices due to the lack of hardware and software resources to support automatic differentiation. This…

Machine Learning · Computer Science 2023-10-11 Yequan Zhao , Xinling Yu , Zhixiong Chen , Ziyue Liu , Sijia Liu , Zheng Zhang

This paper proposes Quantizable DNNs, a special type of DNNs that can flexibly quantize its bit-width (denoted as `bit modes' thereafter) during execution without further re-training. To simultaneously optimize for all bit modes, a…

Computer Vision and Pattern Recognition · Computer Science 2020-04-14 Kunyuan Du , Ya Zhang , Haibing Guan

In this paper we present a a deep generative model for lossy video compression. We employ a model that consists of a 3D autoencoder with a discrete latent space and an autoregressive prior used for entropy coding. Both autoencoder and prior…

Image and Video Processing · Electrical Eng. & Systems 2020-05-11 Amirhossein Habibian , Ties van Rozendaal , Jakub M. Tomczak , Taco S. Cohen

Network quantization has rapidly become one of the most widely used methods to compress and accelerate deep neural networks. Recent efforts propose to quantize weights and activations from different layers with different precision to…

Machine Learning · Computer Science 2020-03-18 Yuhang Li , Wei Wang , Haoli Bai , Ruihao Gong , Xin Dong , Fengwei Yu

Although deep learning models are highly effective for various learning tasks, their high computational costs prohibit the deployment to scenarios where either memory or computational resources are limited. In this paper, we focus on…

Computer Vision and Pattern Recognition · Computer Science 2017-09-14 Cong Leng , Hao Li , Shenghuo Zhu , Rong Jin

This paper investigates compression of data encrypted with block ciphers, such as the Advanced Encryption Standard (AES). It is shown that such data can be feasibly compressed without knowledge of the secret key. Block ciphers operating in…

Information Theory · Computer Science 2010-09-10 Demijan Klinc , Carmit Hazay , Ashish Jagmohan , Hugo Krawczyk , Tal Rabin

We leverage the powerful lossy image compression algorithm BPG to build a lossless image compression system. Specifically, the original image is first decomposed into the lossy reconstruction obtained after compressing it with BPG and the…

Computer Vision and Pattern Recognition · Computer Science 2020-03-24 Fabian Mentzer , Luc Van Gool , Michael Tschannen

The petabyte-scale data generated annually by High Energy Physics (HEP) experiments like those at the Large Hadron Collider present a significant data storage challenge. Whilst traditional algorithms like LZMA and ZLIB are widely used, they…

Computational Physics · Physics 2025-11-17 Akshat Gupta , Caterina Doglioni , Thomas Joseph Elliott

How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational…

Machine Learning · Statistics 2022-12-13 Diederik P Kingma , Max Welling

Memory-efficient continuous Sign Language Translation is a significant challenge for the development of assisted technologies with real-time applicability for the deaf. In this work, we introduce a paradigm of designing recurrent deep…

A new binary (bit-level) lossless compression catalyst method based on a modular arithmetic, called Binary Allocation via Modular Arithmetic (BAMA), has been introduced in this paper. In other words, BAMA is for storage and transmission of…

Information Theory · Computer Science 2014-08-18 Mario Mastriani

Network pruning and quantization are proven to be effective ways for deep model compression. To obtain a highly compact model, most methods first perform network pruning and then conduct network quantization based on the pruned model.…

Computer Vision and Pattern Recognition · Computer Science 2023-05-05 Jing Liu , Bohan Zhuang , Peng Chen , Chunhua Shen , Jianfei Cai , Mingkui Tan

For stochastic models with intractable likelihood functions, approximate Bayesian computation offers a way of approximating the true posterior through repeated comparisons of observations with simulated model outputs in terms of a small set…

Machine Learning · Computer Science 2022-05-24 Carlo Albert , Simone Ulzega , Firat Ozdemir , Fernando Perez-Cruz , Antonietta Mira