Showing 2026Show all
3 papers · 1 filter
stat.ML2026
Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model
Arie Wortsman-Zurich, Hugo Tabanelli, Yatin Dandi +2
We propose a simple mechanism by which scaling laws emerge from feature learning in multi-layer networks. We study a high-dimensional hierarchical target that is a globally high-de…
cs.LG2026
Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
Yatin Dandi, Matteo Vilucchio, Luca Arnaboldi +2
Understanding how deep neural networks learn useful internal representations from data remains a central open problem in the theory of deep learning. We introduce Neural Low-Degree…
stat.ML2026
Deep Learning of Compositional Targets with Hierarchical Spectral Methods
Hugo Tabanelli, Yatin Dandi, Luca Pesce +1
Why depth yields a computational advantage over shallow methods remains a central open question in learning theory. We study this question in a controlled high-dimensional Gaussian…