Showing 2024Show all
3 papers · 1 filter
cs.IT2024
Statistically Valid Information Bottleneck via Multiple Hypothesis Testing
Amirmohammad Farzaneh, Osvaldo Simeone
The information bottleneck (IB) problem is a widely studied framework in machine learning for extracting compressed features that are informative for downstream tasks. However, cur…
cs.IT2024
An Information-Theoretic Analysis of Temporal GNNs
Amirmohammad Farzaneh
Temporal Graph Neural Networks, a new and trending area of machine learning, suffers from a lack of formal analysis. In this paper, information theory is used as the primary tool t…
cs.IT2024
Quantile Learn-Then-Test: Quantile-Based Risk Control for Hyperparameter Optimization
Amirmohammad Farzaneh, Sangwoo Park, Osvaldo Simeone
The increasing adoption of Artificial Intelligence (AI) in engineering problems calls for the development of calibration methods capable of offering robust statistical reliability…