A transformer-based greybox surrogate trained on Monte Carlo data predicts single-qubit gate fidelities under telegraph and Ornstein-Uhlenbeck noise, and gradient-based control with this emulator yields simulated fidelities above 99 percent at low coupling.
The prediction performance for each gate and coupling value is summarized in Table IV, which reports the final training and testing MSE values for each gate
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Machine Learning-aided Optimal Control of a noisy qubit
A transformer-based greybox surrogate trained on Monte Carlo data predicts single-qubit gate fidelities under telegraph and Ornstein-Uhlenbeck noise, and gradient-based control with this emulator yields simulated fidelities above 99 percent at low coupling.