 Most Neural Networks Are Almost LearnableNeural Information Processing Systems (NeurIPS), 2023 |
 Learning to Reason with Neural Networks: Generalization, Unseen Data and
Boolean MeasuresNeural Information Processing Systems (NeurIPS), 2022 |
 From Local Pseudorandom Generators to Hardness of LearningAnnual Conference Computational Learning Theory (COLT), 2021 Amit Daniely Gal Vardi |
 |
 A Deep Conditioning Treatment of Neural NetworksInternational Conference on Algorithmic Learning Theory (ALT), 2020 |
 High Accuracy and High Fidelity Extraction of Neural NetworksUSENIX Security Symposium (USENIX Security), 2019 |
