Simone Bombari

New York University Center for Data Science Flatiron Institute Center for Computational Mathematics Email: simone (dot) bombari [at] nyu (dot) edu [Google Scholar] [GitHub] [X] [LinkedIn]

About Me

I am a Faculty Fellow at the Center for Data Science at New York University and a Research Fellow at the Center for Computational Mathematics at the Flatiron Institute.

My research focuses on deep learning, high-dimensional probability, and trustworthy machine learning. For example, I am interested if large models trained on high-dimensional data hide some not-necessarily-trivial behavior, with maybe some implications connected to robustness or data memorization.

I received my PhD from the Institute of Science and Technology Austria, where I was very fortunate to be advised by Marco Mondelli. Before that, I received my Bachelor and Master in Physics at Scuola Normale Superiore and University of Pisa.

Of course, I have many interests beyond my research. I am quite into fitness, games and cooking.

Selected Publications

• A Sharp Transition in Data Reconstruction under Differential Privacy
  Max Cairney-Leeming, Simone Bombari, Marco Mondelli.

• A Law of Data Reconstruction for Random Features (and Beyond)
  Leonardo Iurada, Simone Bombari, Tatiana Tommasi, Marco Mondelli.

• High-Dimensional Private Linear Regression with Optimal Rates
  Simone Bombari, Jialei Luo, Inbar Seroussi, Marco Mondelli.

• Privacy for Free in the Overparameterized Regime
  Simone Bombari, Marco Mondelli.

• Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels
  Simone Bombari, Shayan Kiyani, Marco Mondelli.

• Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization
  Simone Bombari, Mohammad Hossein Amani, Marco Mondelli.

See Publications for all publications and preprints.