3 citations · 5 across the 15 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Learning as Observable Matrix Dynamics: Diffusive Relaxations versus Phase Transitions
Igor Halperin
Observable Matrix Dynamics (OMD) is a diagnostic framework that probes the dynamics of high-dimensional internal representations of inputs by a neural network via a fixed-size $N \…
cs.LG2026
I-BBS: Coordinate-Free Inference of Latent Sub-Manifolds Using Random Distance Matrix Theory
Igor Halperin
Bogomolny, Bohigas and Schmit (BBS) found that the spectrum of the pairwise distance matrix on N points sampled from a smooth d-dimensional manifold encodes a signature of the unde…