Author

andrea Combette

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Aug 2026

Correlation flow governs learning at criticality

Combining mean-field theory and random matrix theory, a direct link between correlation propagation and the Neural Tangent Kernel (NTK) is established that governs learning in the sequential limit of infinitely wide, infinitely deep networks.

andrea Combette, Nelly Pustelnik, Antoine Venaille · 0 citations