ISIT 2023

166 papers
The 2023 edition of the International Symposium on Information Theory (ISIT) featured 179 papers addressing a broad spectrum of information-theoretic research. A substantial number of contributions focused on the intersection of information theory and machine learning, specifically addressing federated learning, algorithmic stability, and generalization. Research directions included the regularization of empirical risk using f-divergences and the analysis of machine learning models beyond the independent and identically distributed (IID) assumption. Technical contributions also emphasized high-dimensional estimation and matrix recovery, with studies on entrywise error analysis for low-rank matrices and spectral filtering for robust estimation. Distributed computing was explored through coded parallelism for deep learning and robust load balancing for heavy-tailed workloads. Other topics included secure gradient aggregation, goal-oriented compression, and error correction for substring edits. Prolific contributors to the year's proceedings included Bo Bai, Antonia Wachter-Zeh, and Deniz Gündüz, reflecting expertise in coding theory, communication systems, and statistical learning.

Top Research Directions

Research directions most represented by ISIT 2023 papers.

Sparsity Preserving Coded Computation 2
Threshold Saturation via Spatially Coupled Codes 2
Algebraic Redundancy for Straggler Resilient Distributed Systems 2
Decoupling Statistical Dependencies via Poissonization 1
Numerical Stability in Coded Distributed Computing 1
Non-Adaptive Experimental Design via Randomized Pooling 1
The Log-Rank Conjecture in Communication Complexity 1
The Computational Overhead of Adaptive Sampling 1
Unsourced Random Access via Shared Codebooks 1
Characterizing Capacity Achieving Input Distributions under Physical Constraints 1
Robust Group Testing for Noisy Measurements 1
Density Evolution for Asymptotic Analysis of Iterative Decoders 1
Proving Streaming Space Lower Bounds via Communication Complexity 1
Information Theoretic Limits of Correlated Graph Alignment 1
Decoding Thresholds and Capacity via Code Symmetry 1

Top Authors

AuthorPapers
Antonia Wachter-Zeh6
Bo Bai6
Deniz Gunduz6
Ilan Shomorony5
Rawad Bitar5
Flavio Calmon4
Maximilian Egger4
Oliver Kosut4
Anuran Makur3
Christina Fragouli3
Cong Shen3
Dor Elimelech3
Olgica Milenkovic3
Shahab Asoodeh3
Aditya Ramamoorthy2
Alejandro Lancho2
Alex Dytso2
Ashish J Khisti2
Banghua Zhu2
Basak Guler2

Impactful Papers

Papers from ISIT 2023 that shaped research clusters.

Influential

Papers

Title
On Semi-Supervised Estimation of Distributions
On Strong Secrecy for Multiple Access Channel with States and causal CSI
On the Advantages of Asynchrony in the Unsourced MAC
On the best approximation by finite Gaussian mixtures
On the Generalization Error of Meta Learning for the Gibbs Algorithm
On the Gibbs Exponential Mechanism and Private Synthetic Data Generation
On the Inevitability of the Rashomon Effect
On the Optimal Bounds for Noisy Computing
On the Validation of Gibbs Algorithms: Training Datasets, Test Datasets and their Aggregation
Optimal Compression of Unit Norm Vectors in the High Distortion Regime
Optimal List Decoding from Noisy Entropy Inequality
Optimal Multidimensional Differentially Private Mechanisms in the Large-Composition Regime
Optimal Subspace Perturbation Bounds under Gaussian Noise
Optimal Uncorrelated Polyphase ZCZ Sequences over an Alphabet of Minimum size
Perfect vs. Independent Feedback in the Multiple-Access Channel
Permutation Sum-Capacity of Binary Adder Multiple-Access Channels
Personalized PCA for Federated Heterogeneous Data
Perturbation-Resilient Sets for Dynamic Service Balancing
Pointwise Sliced Mutual Information for Neural Network Explainability
Principled OOD Detection via Multiple Testing
Private Aggregation in Wireless Federated Learning with Heterogeneous Clusters
Quadratic Functional Encryption for Secure Training in Vertical Federated Learning
Quantized-Constraint Concatenation and the Covering Radius of Constrained Systems
Quickest Inference of Susceptible-Infected Cascades in Sparse Networks
Randomized Decoding of Linearized Reed-Solomon Codes Beyond the Unique Decoding Radius
Rate Distortion via Constrained Estimated Mutual Information Minimization
Rateless Coding for Multi-Hop Broadcast Transmission in Wireless IoT Networks
Rate-limited Quantum-to-Classical Optimal Transport: A Lossy Source Coding Perspective
Rectangular Rotational Invariant Estimator for General Additive Noise Matrices
Reduced-Complexity Erasure Decoding of Low-Rate Reed-Solomon Codes Based on LCH-FFT
Reliable Throughput of Generalized Collision Channel without Synchronization
Repair of Reed-Solomon Codes in the Presence of Erroneous Nodes
Reward Teaching for Federated Multi-armed Bandits
S3GD-MV: Sparse-SignSGD with Majority Vote for Communication-Efficient Distributed Learning
Schrödinger Mechanisms: Optimal Differential Privacy Mechanisms for Small Sensitivity
Secure Aggregation for Clustered Federated Learning
Secure Embedding Aggregation for Federated Representation Learning
Secure Gradient Aggregation for Wireless Multi-Server Federated Learning
Semantic Communication of Learnable Concepts
Sparse and Private Distributed Matrix Multiplication with Straggler Tolerance
Streaming Erasure Codes over Multicast Relayed Networks
Strong Data Processing Inequalities for Locally Differentially Private Mechanisms
Substring Density Estimation from Traces
Testing for the Bradley-Terry-Luce Model
The Asymptotic Distribution of the Stochastic Mirror Descent Iterates in Linear Models
The Capacity of Channels with O(1)-Bit Feedback
The Cardinality Bound on the Information Bottleneck Representations is Tight
The Learning and Communication Complexity of Subsequence Containment
The Min-entropy of Distributed Wireless Link Scheduling Algorithms under Arbitrary Interference
The Optimal Rate of Second-Order Generalized-Covering Codes

« prev Page 3/4 next »