SOURCE-LINKED INTELLIGENCE

Symmetry without a manifold: intrinsic dimension on orbits

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

The standard geometric derivation of neural scaling exponents takes the intrinsic dimension of a data manifold as its input. On modular addition in $\mathbb{Z}_p$ that derivation has no input. The exact algebraic solution is an orbit of $\mathbb{Z}_p$ acting by isometries. Transitivity alone makes the ratio statistic underlying the standard dimension estimator a point mass, so the estimator is undefined, and here the two nearest neighbour distances coincide exactly. Breaking the symmetry at scale $ε$ returns a number, but one that tracks $1/ε$ with no scale free plateau. We show that the failu

Read original source ↗ Open in workspace

recordType

paper

region

Global