Metric Rarity and the Emergence of Symmetry in G-Invariant Potential Surfaces
Irmi Schneider

TL;DR
This paper investigates the geometric rarity of symmetric solutions in G-invariant optimization landscapes, revealing that symmetric critical points dominate due to the super-exponential decay of asymmetric regions, and explains the prevalence of symmetry in natural phenomena.
Contribution
It introduces a measure-theoretic framework linking group symmetries to the geometric rarity of asymmetric solutions and explains the emergence of symmetry in optimization landscapes.
Findings
The volume of the real image L decays super-exponentially with group size.
Symmetric critical points are statistically dominant due to the rarity of asymmetric regions.
The global gradient directs solutions toward symmetric boundary strata, explaining symmetry emergence.
Abstract
Let X be an irreducible complex affine algebraic variety defined over , equipped with a faithful action of a finite group G, and let Y = X // G denote the categorical quotient with projection . We study the geometry of the real image and its consequences for G-invariant optimization. Equipping with the measure induced by a G-invariant metric on X, we prove that the relative volume of L in equals , where is the set of involutions of G. For the symmetric group acting on , this ratio decays super-exponentially in n. In particular, L is metrically rare within the ambient real quotient. We apply this result to two phenomena observed in G-invariant optimization problems: Regime I (Rarity of asymmetric critical points). The…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsStochastic Gradient Optimization Techniques · Statistical Mechanics and Entropy · Markov Chains and Monte Carlo Methods
