Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
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 +6
Many real-world datasets contain hidden structure that cannot be detected by simple linear correlations between input features. For example, latent factors may influence the data i…
stat.ML2026
Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws
Fabrizio Boncoraglio, Vittorio Erba, Emanuele Troiani +3
Trained attention layers exhibit striking and reproducible spectral structure of the weights, including low-rank collapse, bulk deformation, and isolated spectral outliers, yet the…
stat.ML2026
The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
Vittorio Erba, Emanuele Troiani, Lenka Zdeborová +2
We study the high-dimensional asymptotics of empirical risk minimization (ERM) in over-parametrized two-layer neural networks with quadratic activations trained on synthetic data.…