2 papers
math.ST2025
Robustness of OLS to sample removals: Theoretical analysis and implications
Eyar Azar, Michael J. Feldman, Boaz Nadler
For learned models to be trustworthy, it is essential to verify their robustness to perturbations in the training data. Classical approaches involve uncertainty quantification via…
stat.ML2024
Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data
Eyar Azar, Boaz Nadler
The premise of semi-supervised learning (SSL) is that combining labeled and unlabeled data yields significantly more accurate models. Despite empirical successes, the theoretical u…