Vittorio Erba

According to our database, Vittorio Erba authored at least 15 papers between 2019 and 2026.

Collaborative distances:

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

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

Inductive Bias and Spectral Properties of Single-Head Attention in High Dimensions.

Fabrizio Boncoraglio, Vittorio Erba, Emanuele Troiani, Florent Krzakala, Lenka Zdeborová

CoRR, September, 2025

Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime.

Leonardo Defilippis, Yizhou Xu, Julius Girardin, Emanuele Troiani, Vittorio Erba, Lenka Zdeborová, Bruno Loureiro, Florent Krzakala

CoRR, September, 2025

The maximum-average subtensor problem: equilibrium and out-of-equilibrium properties.

Vittorio Erba, Nathan Malo Kupferschmid, Rodrigo Pérez, Lenka Zdeborová

CoRR, June, 2025

The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks.

Vittorio Erba, Emanuele Troiani, Lenka Zdeborová, Florent Krzakala

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Bayes optimal learning of attention-indexed models.

Fabrizio Boncoraglio, Emanuele Troiani, Vittorio Erba, Lenka Zdeborová

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

2024

Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens.

Vittorio Erba, Emanuele Troiani, Luca Biggio, Antoine Maillard, Lenka Zdeborová

CoRR, 2024

Asymptotic Characterisation of the Performance of Robust Linear Regression in the Presence of Outliers.

Matteo Vilucchio, Emanuele Troiani, Vittorio Erba, Florent Krzakala

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Les Houches Lectures on Deep Learning at Large & Infinite Width.

Yasaman Bahri, Boris Hanin, Antonin Brossollet, Vittorio Erba, Christian Keup, Rosalba Pacelli, James B. Simon

CoRR, 2023

Asymptotic Characterisation of Robust Empirical Risk Minimisation Performance in the Presence of Outliers.

Matteo Vilucchio, Emanuele Troiani, Vittorio Erba, Florent Krzakala

CoRR, 2023

Statistical mechanics of the maximum-average submatrix problem.

Vittorio Erba, Florent Krzakala, Rodrigo Pérez, Lenka Zdeborová

CoRR, 2023

2022

Optimal denoising of rotationally invariant rectangular matrices.

Emanuele Troiani, Vittorio Erba, Florent Krzakala, Antoine Maillard, Lenka Zdeborová

Proceedings of the Mathematical and Scientific Machine Learning, 2022

2021

Aspects of Data Structure in Machine Learning.

Vittorio Erba

PhD thesis, 2021

2020

The p-Airy distribution.

Sergio Caracciolo, Vittorio Erba, Andrea Sportiello

CoRR, 2020

2019

Intrinsic dimension estimation for locally undersampled data.

Vittorio Erba, Marco Gherardi, Pietro Rotondo

CoRR, 2019