Giacomo Le Pera

Learning as a Geometric Phase Transition: Renormalization Group Flow and Anisotropic Symmetry Breaking in Deep Networks

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 geometry of \[ \mathcal N_{0,L}=\frac1N\sum_{r=1}^{L}\Sigma_{r\to L}\otimes T_{0\to r-1}, \] which entangles forward pullback survival with bac...