Publications
2026
-
A Sharp Transition in Data Reconstruction under Differential Privacy
Max Cairney-Leeming, Simone Bombari, Marco Mondelli.
arXiv preprint, 2026. -
High-Dimensional Private Linear Regression with Optimal Rates
Simone Bombari, Jialei Luo, Inbar Seroussi, Marco Mondelli.
arXiv preprint, 2025 (updated 2026). -
A Law of Data Reconstruction for Random Features (and Beyond)
Leonardo Iurada, Simone Bombari, Tatiana Tommasi, Marco Mondelli.
ICLR, 2026.
2025
-
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
Simone Bombari, Marco Mondelli.
ICML, 2025. Best paper award at the ICLR SCSL workshop. -
Privacy for Free in the Overparameterized Regime
Simone Bombari, Marco Mondelli.
PNAS, 2025.
2024
-
DP-KAN: Differentially Private Kolmogorov-Arnold Networks
Nikita P. Kalinin, Simone Bombari, Hossein Zakerinia, Christoph H. Lampert.
arXiv preprint, 2024. -
Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features
Simone Bombari, Marco Mondelli.
ICML, 2024. -
How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features
Simone Bombari, Marco Mondelli.
ICML, 2024.
2023
-
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels
Simone Bombari, Shayan Kiyani, Marco Mondelli.
ICML, 2023. Selected for oral presentation.
2022
-
Towards Differential Relational Privacy and its use in Question Answering
Simone Bombari, Alessandro Achille, Zijian Wang, Yu-Xiang Wang, Yusheng Xie, Kunwar Yashraj Singh, Srikar Appalaraju, Vijay Mahadevan, Stefano Soatto.
arXiv preprint, 2022. -
Sharp asymptotics on the compression of two-layer neural networks
Mohammad Hossein Amani, Simone Bombari, Marco Mondelli, Rattana Pukdee, Stefano Rini.
Information Theory Workshop, 2022. -
Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization
Simone Bombari, Mohammad Hossein Amani, Marco Mondelli.
NeurIPS, 2022.