← Search

Fabrizio Boncoraglio

2 accepted papers

2026

Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws

ICML 2026spotlight

Trained attention layers exhibit striking and reproducible spectral structure of the weights, including low-rank collapse, bulk deformation, and isolated spectral outliers, yet the origin of these phenomena and their implications for generalization remain poorly understood. We study empirical risk m…

Cited by 0SourceScholar
2025

Bayes optimal learning of attention-indexed models

NeurIPS 2025poster

We introduce the attention-indexed model (AIM), a theoretical framework for analyzing learning in deep attention layers. Inspired by multi-index models, AIM captures how token-level outputs emerge from layered bilinear interactions over high-dimensional embeddings. Unlike prior tractable attention m…

Cited by 0SourcecodeScholar