ISIT 2021

215 papers
The 2021 IEEE International Symposium on Information Theory (ISIT) featured 246 papers addressing core challenges in communication and data processing. A primary research direction involved the intersection of information theory and machine learning, with significant focus on information-theoretic generalization, the bottleneck principle, and high probability generalization bounds. Other prominent themes included semantic communication for wireless image transmission, unsourced random access for massive machine-type communications, and the development of provable guarantees for algorithmic performance. Technical contributions also explored bridging the gap between combinatorial existence and efficient decoding, alongside advancements in parallel architectures for sequential decoding. Notable papers investigated topics such as sparse recovery with shuffled labels, analog joint source-channel coding using deep neural networks, and new uncertainty measures like $t$-entropy. Prolific authors during this edition included Flávio P. Calmon, Antonia Wachter-Zeh, Yury Polyanskiy, and Deniz Gunduz. The year’s research reflected a trend toward integrating deep learning with classical information theory, evidenced by work on distributed interference alignment and Riemannian manifold optimization for learning orthogonal representations.

Top Research Directions

Research directions most represented by ISIT 2021 papers.

The Empirical Validation Gap 7
Quantifying Generalization via Information Leakage 3
Generalization Bounds for Unbounded Loss Functions 3
Straggler-Resilient Coded Computation 3
Data-Dependent Priors for Tight PAC-Bayesian Bounds 2
Threshold Saturation via Spatially Coupled Codes 2
Breaking the Linear Scan Barrier in Private Information Retrieval 2
Inherent Rate Adaptation via Rateless Coding 2
Formulating Complex Problems as Markov Decision Processes 2
The Intractability of Multi-Letter Channel Capacities 2
Joint Latent State and Parameter Estimation 2
Overcoming Idealized Assumptions in Channel Modeling 2
Error Feedback for Compressed Distributed Learning 2
Scaling Mutual Information Estimation to High Dimensions 2
Non-Vacuous Generalization Bounds for Deep Learning 2

Top Authors

AuthorPapers
Antonia Wachter-Zeh7
Ayfer Ozgur6
Jean Honorio6
Flavio Calmon5
Rawad Bitar5
Deniz Gunduz4
Or Ordentlich4
Farzad Farnoud3
Giuseppe Durisi3
Lele Wang3
Oliver Kosut3
Ping Li3
Yihan Zhang3
Yury Polyanskiy3
Abdellatif Zaidi2
Alexandre Graell i Amat2
Alfred O. Hero2
Ali Tajer2
Arya Mazumdar2
Chao Tian2

Impactful Papers

Papers from ISIT 2021 that shaped research clusters.

Influential

Papers

Title
Lower Bounds for Over-the-Air Statistical Estimation
Massive Uncoordinated Access With Random User Activity
Mean-Squared Accuracy of Good-Turing Estimator
Meta-learning Based Beamforming Design for MISO Downlink
Minimax Bounds for Blind Network Inference
Minimizing Quantum Rényi Divergences via Mirror Descent with Polyak Step Size
Minimizing the Age of Incorrect Information for Real-time Tracking of Markov Remote Sources
Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems
Model-Inspired Deep Detection with Low-Resolution Receivers
Mosaics of combinatorial designs for privacy amplification
Multiple Criss-Cross Deletion-Correcting Codes
Multiple Support Recovery Using Very Few Measurements Per Sample
Multiplexing Gain of Modulating Phases Through Reconfigurable Intelligent Surface
Multi-Stream Quickest Detection with Unknown Post-Change Parameters Under Sampling Control
Mutual Information of Neural Network Initialisations: Mean Field Approximations
Near-Optimal Coding for Massive Multiple Access
Network Coding with Myopic Adversaries
Neural Group Testing to Accelerate Deep Learning
Neural Network-based Estimation of the MMSE
Non-binary Codes for Correcting a Burst of at Most 2 Deletions
Nonparametric Matrix Estimation with One-Sided Covariates
Numerically stable coded matrix computations via circulant and rotation matrix embeddings
On conditional Sibson's $\alpha$ -Mutual Information
On Dimension in Graph Convolutional Networks for Distinguishing Random Graph Models
On Graph Matching Using Generalized Seed Side-Information
On Learning Parametric Distributions from Quantized Samples
Online Caching with Optimal Switching Regret
Online Transfer Learning: Negative Transfer and Effect of Prior Knowledge
On maximum-likelihood estimation in the all-or-nothing regime
On Optimal Quaternary Locally Repairable Codes
On optimal relay placement in directional networks
On the Capacity of Latent Variable Private Information Retrieval
On the Connectivity and Giant Component Size of Random K-out Graphs Under Randomly Deleted Nodes
On the Convergence Rates of KNN Density Estimation
On the Feed-Forward Rate-Distortion Function for Stationary and Ergodic Sources
Optimal Codes Correcting Localized Deletions
Optimal Communication Rates and Combinatorial Properties for Common Randomness Generation
Optimal Confidence Sets for the Multinomial Parameter
Optimality of Graph Scanning Statistic for Online Community Detection
Optimality of the Discrete Fourier Transform for Beamspace Massive MU-MIMO Communication
Optimal Mechanism Design for Fresh Data Acquisition
Optimal Rates of Teaching and Learning Under Binary Symmetric Noise
Parallelism versus Latency in Simplified Successive-Cancellation Decoding of Polar Codes
Partial Information Decomposition via Deficiency for Multivariate Gaussians
Phase Transitions for Support Recovery from Gaussian Linear Measurements
Polynomial Approximations of Conditional Expectations in Scalar Gaussian Channels
Private and Secure Coded Computation in Straggler-Exploiting Distributed Matrix Multiplication
Probabilistic Group Testing with a Linear Number of Tests
Protograph-Based Design for QC Polar Codes
Quantization of Random Distributions under KL Divergence

« prev Page 3/5 next »