Simone Bombari
7 Publications
2025 | Published | Journal Article | IST-REx-ID: 19627 | 
Bombari, Simone, and Marco Mondelli. “Privacy for Free in the Overparameterized Regime.” Proceedings of the National Academy of Sciences, vol. 122, no. 15, e2423072122, National Academy of Sciences, 2025, doi:10.1073/pnas.2423072122.
[Published Version]
View
| Files available
| DOI
| WoS
| PubMed | Europe PMC
| arXiv
2024 | Published | Conference Paper | IST-REx-ID: 18973 |
Bombari, Simone, and Marco Mondelli. “Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features.” 41st International Conference on Machine Learning, vol. 235, ML Research Press, 2024, pp. 4300–28.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2024 | Published | Conference Paper | IST-REx-ID: 18972 |
Bombari, Simone, and Marco Mondelli. “How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features.” 41st International Conference on Machine Learning, vol. 235, ML Research Press, 2024, pp. 4267–99.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2023 | Published | Conference Paper | IST-REx-ID: 12859 |
Bombari, Simone, et al. “Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels.” Proceedings of the 40th International Conference on Machine Learning, vol. 202, ML Research Press, 2023, pp. 2738–76.
[Preprint]
View
| Files available
| Download Preprint (ext.)
| arXiv
2022 | Submitted | Preprint | IST-REx-ID: 12860 |
Bombari, Simone, et al. “Towards Differential Relational Privacy and Its Use in Question Answering.” ArXiv, 2203.16701, doi:10.48550/arXiv.2203.16701.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Published | Conference Paper | IST-REx-ID: 12537 |
Bombari, Simone, et al. “Memorization and Optimization in Deep Neural Networks with Minimum Over-Parameterization.” 36th Conference on Neural Information Processing Systems, vol. 35, Neural Information Processing Systems Foundation, 2022, pp. 7628–40.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2022 | Published | Journal Article | IST-REx-ID: 12538 |
Amani, Mohammad Hossein, et al. “Sharp Asymptotics on the Compression of Two-Layer Neural Networks.” IEEE Information Theory Workshop, IEEE, 2022, pp. 588–93, doi:10.1109/ITW54588.2022.9965870.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
1 Grants
Trustworthy Deep Learning Theory: Private Over-Parameterized Models and Robust LLMs
2024-10-01 – 2025-09-14
Google Research
7 Publications
2025 | Published | Journal Article | IST-REx-ID: 19627 |
Bombari, Simone, and Marco Mondelli. “Privacy for Free in the Overparameterized Regime.” Proceedings of the National Academy of Sciences, vol. 122, no. 15, e2423072122, National Academy of Sciences, 2025, doi:10.1073/pnas.2423072122.
[Published Version]
View
| Files available
| DOI
| WoS
| PubMed | Europe PMC
| arXiv
2024 | Published | Conference Paper | IST-REx-ID: 18973 |
Bombari, Simone, and Marco Mondelli. “Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features.” 41st International Conference on Machine Learning, vol. 235, ML Research Press, 2024, pp. 4300–28.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2024 | Published | Conference Paper | IST-REx-ID: 18972 |
Bombari, Simone, and Marco Mondelli. “How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features.” 41st International Conference on Machine Learning, vol. 235, ML Research Press, 2024, pp. 4267–99.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2023 | Published | Conference Paper | IST-REx-ID: 12859 |
Bombari, Simone, et al. “Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels.” Proceedings of the 40th International Conference on Machine Learning, vol. 202, ML Research Press, 2023, pp. 2738–76.
[Preprint]
View
| Files available
| Download Preprint (ext.)
| arXiv
2022 | Submitted | Preprint | IST-REx-ID: 12860 |
Bombari, Simone, et al. “Towards Differential Relational Privacy and Its Use in Question Answering.” ArXiv, 2203.16701, doi:10.48550/arXiv.2203.16701.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Published | Conference Paper | IST-REx-ID: 12537 |
Bombari, Simone, et al. “Memorization and Optimization in Deep Neural Networks with Minimum Over-Parameterization.” 36th Conference on Neural Information Processing Systems, vol. 35, Neural Information Processing Systems Foundation, 2022, pp. 7628–40.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2022 | Published | Journal Article | IST-REx-ID: 12538 |
Amani, Mohammad Hossein, et al. “Sharp Asymptotics on the Compression of Two-Layer Neural Networks.” IEEE Information Theory Workshop, IEEE, 2022, pp. 588–93, doi:10.1109/ITW54588.2022.9965870.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv