The Orbit Dimension Criterion: When Symmetry Improves Trainability in Quantum Models

Equivariant architectures—from CNNs to graph neural networks—are central to many areas of deep learning, yet a precise theoretical understanding of why and when symmetry improves learning remains elusive. We study this question using parameterized quantum models, whose loss landscapes admit an exact geometric characterization via group orbits and measure concentration. We prove a general representation-theoretic criterion: a symmetry group avoids exponentially flat loss landscapes (“barren plateaus”) when the dimension of its largest multiplicity-space block scales polynomially with model size. Systematically comparing four symmetry types—no symmetry, finite point group ($D_{2h}$), continuous Abelian ($U(1)$), and permutation ($S_n$)—we show that $S_n$ uniquely achieves polynomial orbit dimension via Schur–Weyl duality, compressing the effective representation space from exponential to $\Theta (n^2)$. Through numerical experiments, we establish three core findings for equivariant learning: (i) trainability and expressibility are controlled by distinct mechanisms—gradient variance is primarily architecture-dependent (varies by less than a factor of two across tasks), while final error varies by approximately four orders of magnitude depending on task–bias alignment; (ii) symmetry matching is the key determinant of performance—when the task aligns with the model's symmetry, error drops to near-zero ($4\times 10^{-6}$); and (iii) inductive bias exhibits a sharp symmetry-matching threshold—the equivariant advantage persists for up to 20% symmetry breaking (error $\sim 10^{-6}$), then jumps by several orders of magnitude once the ground state leaves the symmetric subspace. These results establish parameterized quantum models as a tractable testbed for equivariant learning theory and provide quantitative guidance for designing symmetric architectures.