Memorization and optimization in deep neural networks with minimum over-parameterization S Bombari, MH Amani, M Mondelli Proc. of the Conference on Neural Information Processing Systems (NeurIPS'22), 2022 | 17 | 2022 |
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels S Bombari, S Kiyani, M Mondelli Proceedings of the 40th International Conference on Machine Learning, 2023 | 8 | 2023 |
Stability, generalization and privacy: Precise analysis for random and NTK features S Bombari, M Mondelli arXiv preprint arXiv:2305.12100, 2023 | 4 | 2023 |
Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features S Bombari, M Mondelli arXiv preprint arXiv:2402.02969, 2024 | 1 | 2024 |
Sharp asymptotics on the compression of two-layer neural networks MH Amani, S Bombari, M Mondelli, R Pukdee, S Rini 2022 IEEE Information Theory Workshop (ITW), 588-593, 2022 | | 2022 |
Towards Differential Relational Privacy and its use in Question Answering S Bombari, A Achille, Z Wang, YX Wang, Y Xie, KY Singh, S Appalaraju, ... arXiv preprint arXiv:2203.16701, 2022 | | 2022 |