Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
The hidden advantage of mask resampling: a theory of masked autoencoders
Jorge Medina Moreira, Lorenzo Bardone, Lenka Zdeborová
Why can masked prediction learn useful representations that unmasked reconstruction misses? We study this question in a high-dimensional model of a masked autoencoder (MAE) trained…
stat.ML2026
The Rules-and-Facts Model for Simultaneous Generalization and Memorization in Neural Networks
Gabriele Farné, Fabrizio Boncoraglio, Lenka Zdeborová
A key capability of modern neural networks is their capacity to simultaneously learn underlying rules and memorize specific facts or exceptions. Yet, theoretical understanding of t…
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 +4
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…