Increasing the number of local patches in a distributed quantum neural network architecture reduces the largest Hessian eigenvalue at minima and introduces a class-dependent outlier structure in the eigenspectrum.
& Perdomo-Ortiz, A
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
quant-ph 2verdicts
UNVERDICTED 2representative citing papers
PCA and t-SNE applied to QAOA parameters from max-cut instances reveal distinct patterns and higher preserved variance for entangled mixing operators at depths 2L and 3L.
citing papers explorer
-
The effect of the number of parameters and the number of local feature patches on loss landscapes in distributed quantum neural networks
Increasing the number of local patches in a distributed quantum neural network architecture reduces the largest Hessian eigenvalue at minima and introduces a class-dependent outlier structure in the eigenspectrum.
-
PCA and t-SNE analysis in the study of QAOA entangled and non-entangled mixing operators
PCA and t-SNE applied to QAOA parameters from max-cut instances reveal distinct patterns and higher preserved variance for entangled mixing operators at depths 2L and 3L.