Lorenzo Bardone

According to our database, Lorenzo Bardone authored at least 6 papers between 2023 and 2026.

Collaborative distances:

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

2026

A theory of learning data statistics in diffusion models, from easy to hard.

Lorenzo Bardone, Claudia Merger, Sebastian Goldt

CoRR, March, 2026

A solvable high-dimensional model where nonlinear autoencoders learn structure invisible to PCA while test loss misaligns with generalization.

Vicente Conde Mendes, Lorenzo Bardone, Cédric Koller, Jorge Medina Moreira, Vittorio Erba, Emanuele Troiani, Lenka Zdeborová

CoRR, February, 2026

2025

Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions.

Fabiola Ricci, Lorenzo Bardone, Sebastian Goldt

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

2024

Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks.

Eszter Székely, Lorenzo Bardone, Federica Gerace, Sebastian Goldt

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

Sliding Down the Stairs: How Correlated Latent Variables Accelerate Learning with Neural Networks.

Lorenzo Bardone, Sebastian Goldt

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

2023

Learning from higher-order statistics, efficiently: hypothesis tests, random features, and neural networks.

Eszter Székely, Lorenzo Bardone, Federica Gerace, Sebastian Goldt

CoRR, 2023