English
Related papers

Related papers: Improving Lossless Compression Rates via Monte Car…

200 papers

Deep latent variable models have seen recent success in many data domains. Lossless compression is an application of these models which, despite having the potential to be highly useful, has yet to be implemented in a practical manner. We…

Machine Learning · Computer Science 2019-01-16 James Townsend , Tom Bird , David Barber

The bits-back argument suggests that latent variable models can be turned into lossless compression schemes. Translating the bits-back argument into efficient and practical lossless compression schemes for general latent variable models,…

Machine Learning · Computer Science 2019-10-03 Friso H. Kingma , Pieter Abbeel , Jonathan Ho

Likelihood-based generative models are the backbones of lossless compression due to the guaranteed existence of codes with lengths close to negative log likelihood. However, there is no guaranteed existence of computationally efficient…

Machine Learning · Computer Science 2020-01-07 Jonathan Ho , Evan Lohn , Pieter Abbeel

We develop a simple and elegant method for lossless compression using latent variable models, which we call 'bits back with asymmetric numeral systems' (BB-ANS). The method involves interleaving encode and decode steps, and achieves an…

Machine Learning · Computer Science 2021-04-23 James Townsend

Good quality video coding for low bit-rate applications is important for transmission over narrow-bandwidth channels and for storage with limited memory capacity. In this work, we develop a previous analysis for image compression at low…

Multimedia · Computer Science 2015-04-27 Yehuda Dar , Alfred M. Bruckstein

We generalize the 'bits back with ANS' method to time-series models with a latent Markov structure. This family of models includes hidden Markov models (HMMs), linear Gaussian state space models (LGSSMs) and many more. We provide…

Machine Learning · Computer Science 2021-05-05 James Townsend , Iain Murray

Current methods which compress multisets at an optimal rate have computational complexity that scales linearly with alphabet size, making them too slow to be practical in many real-world settings. We show how to convert a compression…

Information Theory · Computer Science 2023-02-28 Daniel Severo , James Townsend , Ashish Khisti , Alireza Makhzani , Karen Ullrich

Current methods for compressing neural network weights, such as decomposition, pruning, quantization, and channel simulation, often overlook the inherent symmetries within these networks and thus waste bits on encoding redundant…

Information Theory · Computer Science 2024-10-03 Jiajun He , Gergely Flamich , José Miguel Hernández-Lobato

Most data is automatically collected and only ever "seen" by algorithms. Yet, data compressors preserve perceptual fidelity rather than just the information needed by algorithms performing downstream tasks. In this paper, we characterize…

Machine Learning · Computer Science 2022-01-31 Yann Dubois , Benjamin Bloem-Reddy , Karen Ullrich , Chris J. Maddison

We propose an approach to lossy source coding, utilizing ideas from Gibbs sampling, simulated annealing, and Markov Chain Monte Carlo (MCMC). The idea is to sample a reconstruction sequence from a Boltzmann distribution associated with an…

Information Theory · Computer Science 2016-11-17 Shirin Jalali , Tsachy Weissman

While deep neural networks are a highly successful model class, their large memory footprint puts considerable strain on energy consumption, communication bandwidth, and storage requirements. Consequently, model size reduction has become an…

Machine Learning · Statistics 2018-10-02 Marton Havasi , Robert Peharz , José Miguel Hernández-Lobato

Distributed learning methods have gained substantial momentum in recent years, with communication overhead often emerging as a critical bottleneck. Gradient compression techniques alleviate communication costs but involve an inherent…

Machine Learning · Computer Science 2025-07-09 Ze'ev Zukerman , Bassel Hamoud , Kfir Y. Levy

As nowadays Machine Learning (ML) techniques are generating huge data collections, the problem of how to efficiently engineer their storage and operations is becoming of paramount importance. In this article we propose a new lossless…

Data Structures and Algorithms · Computer Science 2022-03-31 Paolo Ferragina , Travis Gagie , Dominik Köppl , Giovanni Manzini , Gonzalo Navarro , Manuel Striani , Francesco Tosoni

Common representations of light fields use four-dimensional data structures, where a given pixel is closely related not only to its spatial neighbours within the same view, but also to its angular neighbours, co-located in adjacent views.…

Image and Video Processing · Electrical Eng. & Systems 2022-02-03 João M. Santos , Lucas A. Thomaz , Pedro A. A. Assunção , Luís A. da Silva Cruz , Luís Távora , Sérgio M. M. Faria

We present a modification to variational Monte Carlo's linear method optimization scheme that addresses a critical memory bottleneck while maintaining compatibility with both the traditional ground state variational principle and our…

Strongly Correlated Electrons · Physics 2017-02-07 Luning Zhao , Eric Neuscamman

Lossless image coding is a crucial task especially in the medical area, e.g., for volumes from Computed Tomography or Magnetic Resonance Tomography. Besides lossless coding, compensated wavelet lifting offers a scalable representation of…

Image and Video Processing · Electrical Eng. & Systems 2023-01-12 Wolfgang Schnurrer , Tobias Tröger , Thomas Richter , Jürgen Seiler , André Kaup

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

We consider the problem of lossy image compression with deep latent variable models. State-of-the-art methods build on hierarchical variational autoencoders (VAEs) and learn inference networks to predict a compressible latent representation…

Image and Video Processing · Electrical Eng. & Systems 2021-01-11 Yibo Yang , Robert Bamler , Stephan Mandt

High-dimensional data are routinely collected in many areas. We are particularly interested in Bayesian classification models in which one or more variables are imbalanced. Current Markov chain Monte Carlo algorithms for posterior…

Methodology · Statistics 2024-01-15 Deborshee Sen , Matthias Sachs , Jianfeng Lu , David Dunson

This paper introduces the notion of soft bits to address the rate-distortion optimization for learning-based image compression. Recent methods for such compression train an autoencoder end-to-end with an objective to strike a balance…

Image and Video Processing · Electrical Eng. & Systems 2019-05-02 David Alexandre , Chih-Peng Chang , Wen-Hsiao Peng , Hsueh-Ming Hang
‹ Prev 1 2 3 10 Next ›