2 papers
cs.IT2025
Unsourced Random Access
Kirill Andreev, Pavel Rybin, Alexey Frolov
Current wireless networks are designed to optimize spectral efficiency for human users, who typically require sustained connections for high-data-rate applications like file transf…
cs.LG2024
Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression
Ivan Butakov, Alexander Tolmachev, Sofia Malanchuk +3
The Information Bottleneck (IB) principle offers an information-theoretic framework for analyzing the training process of deep neural networks (DNNs). Its essence lies in tracking…