Research
AI Predicts Optimal Parameters for Sample-based Quantum Diagonalization
Researchers trained machine learning models to select configuration parameters for Sample-based Quantum Diagonalization (SQD) methods, which compute molecular ground-state energies. The models predict simulation error and runtime from Hamiltonian and configuration, achieving strong rank correlations (Spearman ρ=0.969 for error, 0.905 for runtime) on synthetic Hamiltonians. For 50 molecular Hamiltonians and 600 SqDRIFT hardware runs, classifiers distinguish configurations reaching chemical accuracy, with balanced accuracy 61.8% in-distribution and 100% for five larger held-out molecules.
Sample-based Quantum DiagonalizationAI for quantum chemistryParameter optimization