Simone Bombari

According to our database, Simone Bombari authored at least 11 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Better Rates for Private Linear Regression in the Proportional Regime via Aggressive Clipping.

Simone Bombari, Inbar Seroussi, Marco Mondelli

CoRR, May, 2025

Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization.

Simone Bombari, Marco Mondelli

CoRR, February, 2025

2024

Privacy for Free in the Over-Parameterized Regime.

Simone Bombari, Marco Mondelli

CoRR, 2024

DP-KAN: Differentially Private Kolmogorov-Arnold Networks.

Nikita P. Kalinin, Simone Bombari, Hossein Zakerinia, Christoph H. Lampert

CoRR, 2024

Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features.

Simone Bombari, Marco Mondelli

Proceedings of the Forty-first International Conference on Machine Learning, 2024

How Spurious Features are Memorized: Precise Analysis for Random and NTK Features.

Simone Bombari, Marco Mondelli

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Stability, Generalization and Privacy: Precise Analysis for Random and NTK Features.

Simone Bombari, Marco Mondelli

CoRR, 2023

Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels.

Simone Bombari, Shayan Kiyani, Marco Mondelli

Proceedings of the International Conference on Machine Learning, 2023

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

CoRR, 2022

Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization.

Simone Bombari, Mohammad Hossein Amani, Marco Mondelli

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Sharp asymptotics on the compression of two-layer neural networks.

Mohammad Hossein Amani, Simone Bombari, Marco Mondelli, Rattana Pukdee, Stefano Rini

Proceedings of the IEEE Information Theory Workshop, 2022