activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks

Julius Girardin, Emanuele Troiani, Yizhou Xu +3

Understanding how performance scales jointly with model size and data is a central problem in modern machine learning. Existing theoretical works on scaling laws typically describe…

cs.LG2026

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

Leonardo Defilippis, Yizhou Xu, Julius Girardin +6

Neural scaling laws underlie many of the recent advances in deep learning, yet their theoretical understanding remains largely confined to linear models. In this work, we present a…

cs.LG2026

Bayes optimal learning of attention-indexed models

Fabrizio Boncoraglio, Emanuele Troiani, Vittorio Erba +2

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-leve…

cs.LG2025

Fundamental computational limits of weak learnability in high-dimensional multi-index models

Emanuele Troiani, Yatin Dandi, Leonardo Defilippis +3

Multi-index models - functions which only depend on the covariates through a non-linear transformation of their projection on a subspace - are a useful benchmark for investigating…

cs.LG2025

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

Emanuele Troiani, Hugo Cui, Yatin Dandi +2

In this manuscript, we study the learning of deep attention neural networks, defined as the composition of multiple self-attention layers, with tied and low-rank weights. We first…