English
Related papers

Related papers: Algorithmic Polarization for Hidden Markov Models

200 papers

The Parity Source Coder is a protocol for data compression which is based on a set of parity checks organized in a sparse random network. We consider here the case of memoryless unbiased binary sources. We show that the theoretical capacity…

Disordered Systems and Neural Networks · Physics 2009-11-11 Stefano Ciliberti , Marc Mezard

Polar codes are a new class of capacity-achieving error-correcting codes with low encoding and decoding complexity. Their low-complexity decoding algorithms rendering them attractive for use in software-defined radio applications where…

Information Theory · Computer Science 2016-07-12 Pascal Giard , Gabi Sarkis , Camille Leroux , Claude Thibeault , Warren J. Gross

Quantum reading provides a general framework where to formulate the statistical discrimination of quantum channels. Several paths have been taken for such a problem. However, there is much to be done in the avenue of optimizing channel…

Information Theory · Computer Science 2022-06-22 Francisco Revson F. Pereira , Stefano Mancini

Holevo, Schumacher, and Westmoreland's coding theorem guarantees the existence of codes that are capacity-achieving for the task of sending classical data over a channel with classical inputs and quantum outputs. Although they demonstrated…

Quantum Physics · Physics 2013-01-21 Mark M. Wilde , Saikat Guha

Decentralized optimization methods enable on-device training of machine learning models without a central coordinator. In many scenarios communication between devices is energy demanding and time consuming and forms the bottleneck of the…

Optimization and Control · Mathematics 2020-11-04 Dmitry Kovalev , Anastasia Koloskova , Martin Jaggi , Peter Richtarik , Sebastian U. Stich

In this paper, we leverage polar codes and the well-established channel polarization to design capacity-achieving codes with a certain constraint on the weights of all the columns in the generator matrix (GM) while having a low-complexity…

Information Theory · Computer Science 2023-03-17 James Chin-Jen Pang , Hessam Mahdavifar , S. Sandeep Pradhan

We study polar coding for stochastic processes with memory. For example, a process may be defined by the joint distribution of the input and output of a channel. The memory may be present in the channel, the input, or both. We show that…

Information Theory · Computer Science 2018-08-16 Eren Sasoglu , Ido Tal

Classical source polar codes require the construction of frozen sets for given sources. While this scheme offers excellent theoretical performance, it faces challenges in practical data compression systems, including sensitivity to the…

Information Theory · Computer Science 2025-01-23 Zichang Ren , Yuping Zhao

The problem of high-dimensional and large-scale representation of visual data is addressed from an unsupervised learning perspective. The emphasis is put on discrete representations, where the description length can be measured in bits and…

Machine Learning · Computer Science 2019-01-25 Sohrab Ferdowsi

We develop a low-complexity polar coding scheme for the discrete memoryless broadcast channel with confidential messages under strong secrecy and randomness constraints. Our scheme extends previous work by using an optimal rate of uniform…

Information Theory · Computer Science 2016-03-08 Remi A. Chou , Matthieu R. Bloch

A transform that is universally polarizing over a set of channels with memory is presented. Memory may be present in both the input to the channel and the channel itself. Both the encoder and the decoder are aware of the input distribution,…

Information Theory · Computer Science 2024-09-13 Boaz Shuval , Ido Tal

Real-world multichannel time series prediction faces growing demands for efficiency across edge and cloud environments, making channel compression a timely and essential problem. Motivated by the success of Multiple-Input Multiple-Output…

Machine Learning · Computer Science 2026-01-30 Ziqi Liu , Pei Zeng , Yi Ding

Lossy gradient compression has become a practical tool to overcome the communication bottleneck in centrally coordinated distributed training of machine learning models. However, algorithms for decentralized training with compressed…

Machine Learning · Computer Science 2020-10-20 Thijs Vogels , Sai Praneeth Karimireddy , Martin Jaggi

We study the problem of efficient compression of a stochastic source of probability distributions. It can be viewed as a generalization of Shannon's source coding problem. It has relation to the theory of common randomness, as well as to…

Quantum Physics · Physics 2016-09-08 Andreas Winter

Consider a lossy compression system with $\ell$ distributed encoders and a centralized decoder. Each encoder compresses its observed source and forwards the compressed data to the decoder for joint reconstruction of the target signals under…

Information Theory · Computer Science 2018-07-19 Yizhong Wang , Li Xie , Xuan Zhang , Jun Chen

When a neural network (NN) is used to decode a polar code, its training complexity scales exponentially as the code block size (or to be precise, as a number of message bits) increases. Therefore, existing solutions that use a neural…

Information Theory · Computer Science 2022-11-10 Evgeny Stupachenko

Can we use machine learning to compress graph data? The absence of ordering in graphs poses a significant challenge to conventional compression algorithms, limiting their attainable gains as well as their ability to discover relevant…

Machine Learning · Computer Science 2023-09-26 Giorgos Bouritsas , Andreas Loukas , Nikolaos Karalias , Michael M. Bronstein

The use of parity-check gates in information theory has proved to be very efficient. In particular, error correcting codes based on parity checks over low-density graphs show excellent performances. Another basic issue of information…

Disordered Systems and Neural Networks · Physics 2007-05-23 S. Ciliberti , M. Mezard , R. Zecchina

Coded source compression, also known as source compression with helpers, has been a major variant of distributed source compression, but has hitherto received little attention in the quantum regime. This work treats and solves the…

Information Theory · Computer Science 2019-03-08 Min-Hsiu Hsieh , Shun Watanabe

We study a hidden Markov process which is the result of a transmission of the binary symmetric Markov source over the memoryless binary symmetric channel. This process has been studied extensively in Information Theory and is often used as…

Dynamical Systems · Mathematics 2015-09-11 Evgeny Verbitskiy