A coherence law based on the readout-visible aligned coherence rate (a Rayleigh quotient of the noise generator) predicts gradient survival in noisy U(1)-equivariant QNNs, with simulations confirming R²=0.979 and a special channel test showing no loss where predicted.
Marvian R
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Haar random qubit states show vanishing fermionic non-Gaussianity for subsystems smaller than half the total size without symmetry, small but finite non-Gaussianity with U(1) symmetry, and extensive non-Gaussianity for larger subsystems.
citing papers explorer
-
A Coherence Law for Trainability in Noisy Equivariant Quantum Neural Networks
A coherence law based on the readout-visible aligned coherence rate (a Rayleigh quotient of the noise generator) predicts gradient survival in noisy U(1)-equivariant QNNs, with simulations confirming R²=0.979 and a special channel test showing no loss where predicted.