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
Quantum Broadcast Channels with Cooperating Decoders: An Information-Theoretic Perspective on Quantum Repeaters
Quickest Dynamic Anomaly Detection in Anonymous Heterogeneous Sensor Networks
Reconstruction on 2D Regular Grids
Reed-Muller Subcodes: Machine Learning-Aided Design of Efficient Soft Recursive Decoding
Regret Bounds for Safe Gaussian Process Bandit Optimization
Regularized Loss Minimizers with Local Data Perturbation: Consistency and Data Irrecoverability
Regular Multiset Combinatorial Batch Codes over Vector Spaces
Repairing Reed-Solomon Codes Evaluated on Subspaces
Resolution Limits of Non-Adaptive 20 Questions Estimation for Multiple Targets
Retrieving Data Permutations from Noisy Observations: High and Low Noise Asymptotics
Revisiting Context-Tree Weighting for Bayesian Inference
Robust Machine Learning via Privacy/ Rate-Distortion Theory
Scalable Vector Gaussian Information Bottleneck
SDP Methods for Sensitivity-Constrained Privacy Funnel and Information Bottleneck Problems
Self-Regularity of Output Weights for Overparameterized Two-Layer Neural Networks
Semi-Blind Channel Estimation for RIS-Aided Massive MIMO: A Trilinear AMP Approach
Semiquantitative Group Testing in at Most Two Rounds
Sequential Change Detection of a Correlation Structure under a Sampling Constraint
Sets of Marginals and Pearson-Correlation-based CHSH Inequalities for a Two-Qubit System
Sharp Asymptotics of Matrix Sketching for a Rank-One Spiked Model
Sharp Maximum-Entropy Comparisons
Single-RF Multi-User Communication Through Reconfigurable Intelligent Surfaces: An Information-Theoretic Analysis
Singleton-Optimal LRCs and Perfect LRCs via Cyclic Codes
Sketching and Sequence Alignment: A Rate-Distortion Perspective
Small-Sample Inferred Adaptive Recoding for Batched Network Coding
Soft-covering via Constant-composition Superposition codes
Sparse Multi-Decoder Recursive Projection Aggregation for Reed-Muller Codes
Sparse Recovery with Shuffled Labels: Statistical Limits and Practical Estimators
Speeding Up Private Distributed Matrix Multiplication via Bivariate Polynomial Codes
Streaming Erasure Codes over Multi-Access Relay Networks
Strong data processing inequality in neural networks with noisy neurons and its implications
Strong Secrecy of Arbitrarily Varying Wiretap Channels with Constraints by Stochastic Code
Sub-Gaussian Error Bounds for Hypothesis Testing
Successively Solvable Shift-Add Systems - a Graphical Characterization
Support Estimation with Sampling Artifacts and Errors
Symmetry and the Entropy of Small-World Structures and Graphs
The Discrepancy Attack on Polyshard-ed Blockchains
The Double-Sided Information-Bottleneck Function
The Generalized Covering Radii of Linear Codes
The Impact of Split Classifiers on Group Fairness
The Postdoc Problem under the Mallows Model
The Switching Hierarchical Gaussian Filter
Tight List-Sizes for Oblivious AVCs under Constraints
Time-Correlated Sparsification for Communication-Efficient Federated Learning
Timely Broadcasting in Erasure Networks: Age-Rate Tradeoffs
Towards Secure Over-The-Air Computation
Transfer Learning in Bandits with Latent Continuity
Trellis BMA: Coded Trace Reconstruction on IDS Channels for DNA Storage
Two Dimensional Deletion Correcting Codes and their Applications
Two-Level Private Information Retrieval

« prev Page 4/5 next »