About the Information Theory Society
Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua.
Who are we?
What do we do?
Learn More About ITSOC
Get Involved
Information theory is the study of the mathematical fundamentals of information transmission and storage.
Plain
Attend A Conference
Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt.
Meet It Society Students
Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt.
Submit A Paper
Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt.News
Robert Calderbank - USC Viterbi Lecture, Thursday March 2, 2023
Robert Calderbank of Duke University will give the 2023 USC Viterbi Lecture on Thursday, March 2,…
Feb 28, 2023
Submission Deadline Approaching: JSAIT Issue on Role of Freshness and Semantic Measures
Call for Papers for JSAIT Issue on the Role of Freshness and Semantic Measures in the Transmission…
Feb 17, 2023
IEEE Information Theory Society Call for 2023 Award Nominations
Nominations are now open for paper awards as well as annual awards and recognition from the IEEE…
Jan 9, 2023
Aylin Yener Has Been Elected To Be the Next IEEE Division IX Director
The IT Society congratulates our Past President Aylin Yener for being elected to be the next IEEE…
Dec 22, 2022
Conferences
Jobs
Postdoctoral Researcher Position on Information Theory and Coding
Bilkent University
Immediate openings for postdocs on insertion/deletion channels and DNA storage at Bilkent…
Mar 3, 2023
Postdoc Positions in Wireless Communications
University of Hawaii
Department of Electrical and Computer Engineering at University of Hawaii is looking for two…
Feb 22, 2023
Postdoctoral Position in Econometrics and Statistics
University of Vienna-Department of Statistics and Operations Research
The University of Vienna invites applications for a postdoctoral position in the field of…
Feb 10, 2023
Call to Action
IEEE BITS the Information Theory Magazine
IEEE BITS the Information Theory Magazine publishes content that includes tutorials and review articles, historical surveys, and columns. The tutorial and review articles cover both traditional and emerging areas associated with Information Theory research and are written in a style accessible to readers outside the specialty of the article. The historical surveys are intended to highlight technological advances of current interest that have been significantly impacted by past Information Theory research.
Most recent issue
Magazine web site
Submit an article
Recent Journal Issues
IEEE Journal on Selected Areas in Information Theory
IEEE Journal on Selected Areas in Information Theory
IEEE Transactions on Information Theory
The IEEE Transactions on Information Theory publishes papers concerned with the transmission, processing, and utilization of information.
Plain
Videos on Information Theory
Find tutorials, lectures, keynotes and technical presentations on information theory
Research In Information Theory
Selected papers on information theory from our journals and conferences
IEEE JSAIT on the Information Theory Magazine
JPEG Compliant Compression for DNN Vision
Conventional image compression techniques are primarily developed for the human visual system. However, with the extensive use of deep neural networks (DNNs) for computer vision, more and more images will be consumed by DNN-based intelligent machines, which makes it crucial to develop image compression techniques customized for DNN vision while being JPEG compliant. In this paper, we revisit the JPEG rate distortion theory for DNN vision. First, we propose a novel distortion measure, dubbed the sensitivity weighted error (SWE), for DNN vision.
IEEE JSAIT on the Information Theory Magazine
Throughput and Latency Analysis for Line Networks With Outage Links
Wireless communication links suffer from outage events caused by fading and interference. To facilitate a tractable analysis of network communication throughput and latency, we propose an outage link model to represent a communication link in the slow fading phenomenon. For a line-topology network with outage links, we study three types of intermediate network node schemes: random linear network coding, store-and-forward, and hop-by-hop retransmission. We provide the analytical formulas for the maximum throughputs and the end-to-end latency for each scheme.
IEEE JSAIT on the Information Theory Magazine
Addressing GAN Training Instabilities via Tunable Classification Losses
Generative adversarial networks (GANs), modeled as a zero-sum game between a generator (G) and a discriminator (D), allow generating synthetic data with formal guarantees. Noting that D is a classifier, we begin by reformulating the GAN value function using class probability estimation (CPE) losses. We prove a two-way correspondence between CPE loss GANs and f-GANs which minimize f-divergences. We also show that all symmetric f-divergences are equivalent in convergence.
IEEE JSAIT on the Information Theory Magazine
Information Velocity of Cascaded Gaussian Channels With Feedback
We consider a line network of nodes, connected by additive white noise channels, equipped with local feedback. We study the velocity at which information spreads over this network. For transmission of a data packet, we give an explicit positive lower bound on the velocity, for any packet size. Furthermore, we consider streaming, that is, transmission of data packets generated at a given average arrival rate. We show that a positive velocity exists as long as the arrival rate is below the individual Gaussian channel capacity, and provide an explicit lower bound.
IEEE JSAIT on the Information Theory Magazine
Long-Term Fairness in Sequential Multi-Agent Selection with Positive Reinforcement
While much of the rapidly growing literature on fair decision-making focuses on metrics for one-shot decisions, recent work has raised the intriguing possibility of designing sequential decision-making to positively impact long-term social fairness. In selection processes such as college admissions or hiring, biasing slightly towards applicants from under-represented groups is hypothesized to provide positive feedback that increases the pool of under-represented applicants in future selection rounds, thus enhancing fairness in the long term.
IEEE JSAIT on the Information Theory Magazine
Controlled privacy leakage propagation throughout overlapping grouped learning
Federated Learning (FL) is the standard protocol for collaborative learning. In FL, multiple workers jointly train a shared model. They exchange model updates calculated on their data, while keeping the raw data itself local. Since workers naturally form groups based on common interests and privacy policies, we are motivated to extend standard FL to reflect a setting with multiple, potentially overlapping groups.
IEEE JSAIT on the Information Theory Magazine
Neural Distributed Source Coding
We consider the Distributed Source Coding (DSC) problem concerning the task of encoding an input in the absence of correlated side information that is only available to the decoder. Remarkably, Slepian and Wolf showed in 1973 that an encoder without access to the side information can asymptotically achieve the same compression rate as when the side information is available to it. This seminal result was later extended to lossy compression of distributed sources by Wyner, Ziv, Berger, and Tung.
IEEE JSAIT on the Information Theory Magazine
rTop-k: A Statistical Estimation Approach to Distributed SGD
The large communication cost for exchanging gradients between different nodes significantly limits the scalability of distributed training for large-scale learning models. Motivated by this observation, there has been significant recent interest in techniques that reduce the communication cost of distributed Stochastic Gradient Descent (SGD), with gradient sparsification techniques such as top-k and random-k shown to be particularly effective.
IEEE JSAIT on the Information Theory Magazine
A Unified Approach to Translate Classical Bandit Algorithms to the Structured Bandit Setting
We consider a finite-armed structured bandit problem in which mean rewards of different arms are known functions of a common hidden parameter 8*. Since we do not place any restrictions on these functions, the problem setting subsumes several previously studied frameworks that assume linear or invertible reward functions. We propose a novel approach to gradually estimate the hidden 8* and use the estimate together with the mean reward functions to substantially reduce exploration of sub-optimal arms.
IEEE JSAIT on the Information Theory Magazine
Minimax Estimation of Divergences Between Discrete Distributions
We study the minimax estimation of α-divergences between discrete distributions for integer α ≥ 1, which include the Kullback-Leibler divergence and the χ2-divergences as special examples. Dropping the usual theoretical tricks to acquire independence, we construct the first minimax rate-optimal estimator which does not require any Poissonization, sample splitting, or explicit construction of approximating polynomials.
Distinguished Lecturers
The Distinguished Lecturers program promotes interest in information theory by supporting chapters who wish to invite prominent information theory researchers to give talks at their events.
