3 citations · 3 across the 5 of their papers we have counts for
5 papers
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…
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…
Generalization and Estimation Error Bounds for Model-based Neural Networks
Avner Shultzman, Eyar Azar, Miguel R. D. Rodrigues +1
Model-based neural networks provide unparalleled performance for various tasks, such as sparse coding and compressed sensing problems. Due to the strong connection with the sensing…
Robust Unlimited Sampling Beyond Modulo
Eyar Azar, Satish Mulleti, Yonina C. Eldar
Analog to digital converters (ADCs) act as a bridge between the analog and digital domains. Two important attributes of any ADC are sampling rate and its dynamic range. For bandlim…
Residual Recovery Algorithm For Modulo Sampling
Eyar Azar, Satish Mulleti, Yonina C. Eldar
Two important attributes of analog to digital converters (ADCs) are its sampling rate and dynamic range. The sampling rate should be greater than or equal to the Nyquist rate for b…