233 citations · 531 across the 32 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2023★ 7 cited
The SSL Interplay: Augmentations, Inductive Bias, and Generalization
Vivien Cabannes, Bobak T. Kiani, Randall Balestriero +2
Self-supervised learning (SSL) has emerged as a powerful framework to learn representations from raw data without supervision. Yet in practice, engineers face issues such as instab…
stat.ML2020★ 2 cited
Adversarial Robustness Guarantees for Random Deep Neural Networks
Giacomo De Palma, Bobak T. Kiani, Seth Lloyd
The reliability of deep learning algorithms is fundamentally challenged by the existence of adversarial examples, which are incorrectly classified inputs that are extremely close t…