156 citations · 158 across the 12 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cond-mat.dis-nn2026
Learning as a Geometric Phase Transition: Renormalization Group Flow and Anisotropic Symmetry Breaking in Deep Networks
G. Le Pera, C. Nordio
We formulate feature learning as a geometric critical phenomenon of the lifted tensor-product learning metric. The central object is not a scalar overlap, but the target-active geo…
cs.LG2026
Learning Dynamics Reveal a Hierarchy of Weight-Induced Layerwise Gram Metrics
Claudio Nordio
We study feed-forward ReLU networks with fixed readout and quadratic loss, and rewrite gradient descent as a collective dynamics of activation fields and conjugate fields on the tr…