Emanuele Troiani

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

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

Bayes optimal learning of attention-indexed models

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

Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds