Leonardo Petrini

According to our database, Leonardo Petrini authored at least 8 papers between 2020 and 2023.

Collaborative distances:

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

2023

How deep convolutional neural networks lose spatial information with training.

Umberto M. Tomasini, Leonardo Petrini, Francesco Cagnetta, Matthieu Wyart

Mach. Learn. Sci. Technol., December, 2023

Breaking the Curse of Dimensionality in Deep Neural Networks by Learning Invariant Representations.

Leonardo Petrini

CoRR, 2023

How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model.

Leonardo Petrini, Francesco Cagnetta, Umberto M. Tomasini, Alessandro Favero, Matthieu Wyart

CoRR, 2023

2022

Learning sparse features can lead to overfitting in neural networks.

Leonardo Petrini, Francesco Cagnetta, Eric Vanden-Eijnden, Matthieu Wyart

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

2021

Relative stability toward diffeomorphisms in deep nets indicates performance.

Leonardo Petrini, Alessandro Favero, Mario Geiger, Matthieu Wyart

CoRR, 2021

Relative stability toward diffeomorphisms indicates performance in deep nets.

Leonardo Petrini, Alessandro Favero, Mario Geiger, Matthieu Wyart

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training.

Mario Geiger, Leonardo Petrini, Matthieu Wyart

CoRR, 2020

Compressing invariant manifolds in neural nets.

Jonas Paccolat, Leonardo Petrini, Mario Geiger, Kevin Tyloo, Matthieu Wyart

CoRR, 2020