activity
20242026
collaborators

11 papers

cs.IT2026

Leveraging Code Automorphisms for Improved Syndrome-Based Neural Decoding

Raphaël Le Bidan, Ahmad Ismail, Elsa Dupraz +1

Syndrome-based neural decoding (SBND) has emerged as a promising deep learning approach for soft-decision decoding of high-rate, short-length codes. However, this approach still ha…

cs.IT2026

Doing More With Less: Towards More Data-Efficient Syndrome-Based Neural Decoders

Ahmad Ismail, Raphaël Le Bidan, Elsa Dupraz +1

While significant research efforts have been directed toward developing more capable neural decoding architectures, comparatively little attention has been paid to the quality of t…

stat.ML2026

A Novel Theoretical Analysis for Clustering Heteroscedastic Gaussian Data without Knowledge of the Number of Clusters

Dominique Pastor, Elsa Dupraz, Ismail Hbilou +1

This paper addresses the problem of clustering measurement vectors that are heteroscedastic in that they can have different covariance matrices. From the assumption that the measur…

cs.IT2025

Non-Asymptotic Achievable Rate-Distortion Region for Indirect Wyner-Ziv Source Coding

Jiahui Wei, Philippe Mary, Elsa Dupraz

In the Wyner-Ziv source coding problem, a source has to be encoded while the decoder has access to side information . This paper investigates the indirect setup, in which a…

cs.IT2025

Learning Variable Node Selection for Improved Multi-Round Belief Propagation Decoding

Ahmad Ismail, Raphaël Le Bidan, Elsa Dupraz +1

Error correction at short blocklengths remains a challenge for low-density parity-check (LDPC) codes, as belief propagation (BP) decoding is suboptimal compared to maximum-likeliho…

cs.IT2025

Practical Short-Length Coding Schemes for Binary Distributed Hypothesis Testing

Ismaila Salihou Adamou, Elsa Dupraz, Reza Asvadi +1

This paper addresses the design of practical shortlength coding schemes for Distributed Hypothesis Testing (DHT). While most prior work on DHT has focused on informationtheoretic a…