2 papers
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…
stat.ML2025
High-dimensional learning of narrow neural networks
Hugo Cui
Recent years have been marked with the fast-pace diversification and increasing ubiquity of machine learning applications. Yet, a firm theoretical understanding of the surprising e…