Francesco Cagnetta

According to our database, Francesco Cagnetta authored at least 14 papers between 2021 and 2026.

Collaborative distances:

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

2026

Deriving Neural Scaling Laws from the statistics of natural language.

Francesco Cagnetta, Allan Raventós, Surya Ganguli, Matthieu Wyart

CoRR, February, 2026

Deep networks learn to parse uniform-depth context-free languages from local statistics.

Jack T. Parley, Francesco Cagnetta, Matthieu Wyart

CoRR, February, 2026

2025

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures.

Francesco Cagnetta, Alessandro Favero, Antonio Sclocchi, Matthieu Wyart

CoRR, May, 2025

How Compositional Generalization and Creativity Improve as Diffusion Models are Trained.

Alessandro Favero, Antonio Sclocchi, Francesco Cagnetta, Pascal Frossard, Matthieu Wyart

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Learning curves theory for hierarchically compositional data with power-law distributed features.

Francesco Cagnetta, Hyunmo Kang, Matthieu Wyart

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Towards a theory of how the structure of language is acquired by deep neural networks.

Francesco Cagnetta, Matthieu Wyart

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

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

Kernels, Data & Physics.

Francesco Cagnetta, Deborah Oliveira, Mahalakshmi Sabanayagam, Nikolaos Tsilivis, Julia Kempe

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

What Can Be Learnt With Wide Convolutional Neural Networks?

Francesco Cagnetta, Alessandro Favero, Matthieu Wyart

Proceedings of the International Conference on Machine Learning, 2023

2022

How Wide Convolutional Neural Networks Learn Hierarchical Tasks.

Francesco Cagnetta, Alessandro Favero, Matthieu Wyart

CoRR, 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

PhyDSL_K: a model-driven framework for generating exergames.

Maria Teresa Baldassarre, Danilo Caivano, Simone Romano, Francesco Cagnetta, Víctor Fernández-Cervantes, Eleni Stroulia

Multim. Tools Appl., 2021

Locality defeats the curse of dimensionality in convolutional teacher-student scenarios.

Alessandro Favero, Francesco Cagnetta, Matthieu Wyart

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