A meta-learned initialization scheme that minimizes the log condition number of the Fubini-Study metric is reported to improve trainability and test accuracy of an 8-qubit variational classifier.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sculpting Quantum Landscapes: Fubini-Study Metric Conditioning for Geometry Aware Learning in Parameterized Quantum Circuits
A meta-learned initialization scheme that minimizes the log condition number of the Fubini-Study metric is reported to improve trainability and test accuracy of an 8-qubit variational classifier.