Leonardo Petrini

Publication Activity (10 Years)

Years Active: 2020-2023
Publications (10 Years): 10

Top Topics

Color Histogram

Spatial Information

Top Venues

Mach. Learn. Sci. Technol.

Publications

Umberto M. Tomasini, Leonardo Petrini, Francesco Cagnetta, Matthieu Wyart
How deep convolutional neural networks lose spatial information with training. Mach. Learn. Sci. Technol. 4 (4) (2023)
Leonardo Petrini, Francesco Cagnetta, Umberto M. Tomasini, Alessandro Favero, Matthieu Wyart
How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model. CoRR (2023)
Leonardo Petrini
Breaking the Curse of Dimensionality in Deep Neural Networks by Learning Invariant Representations. CoRR (2023)
Umberto M. Tomasini, Leonardo Petrini, Francesco Cagnetta, Matthieu Wyart
How deep convolutional neural networks lose spatial information with training. CoRR (2022)
Leonardo Petrini, Francesco Cagnetta, Eric Vanden-Eijnden, Matthieu Wyart
Learning sparse features can lead to overfitting in neural networks. NeurIPS (2022)
Leonardo Petrini, Francesco Cagnetta, Eric Vanden-Eijnden, Matthieu Wyart
Learning sparse features can lead to overfitting in neural networks. CoRR (2022)
Leonardo Petrini, Alessandro Favero, Mario Geiger, Matthieu Wyart
Relative stability toward diffeomorphisms in deep nets indicates performance. CoRR (2021)
Leonardo Petrini, Alessandro Favero, Mario Geiger, Matthieu Wyart
Relative stability toward diffeomorphisms indicates performance in deep nets. NeurIPS (2021)
Jonas Paccolat, Leonardo Petrini, Mario Geiger, Kevin Tyloo, Matthieu Wyart
Compressing invariant manifolds in neural nets. CoRR (2020)
Mario Geiger, Leonardo Petrini, Matthieu Wyart
Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training. CoRR (2020)