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.
Exploiting symmetry in variational quantum machine learning,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
quant-ph 2representative citing papers
Fragment classification is efficiently learnable by quantum neural networks under suitable conditions but resists known classical dequantization techniques.
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.