AI for Parameter Selection in Sample-based Quantum Diagonalization
Organizations: IBM Research · ETH Zürich · NCCR Catalysis, Switzerland
Abstract
Sample-based Quantum Diagonalization (SQD) methods provide a way to compute molecular ground-state energies, but their accuracy and runtime depend sensitively on configuration choices such as the subspace dimension, propagation timestep, and the allocation of a fixed sampling budget across circuits, for which no formal selection method exists. In this work, we explore whether oracle models can predict the quantum runtime and approximation error from the Hamiltonian and the candidate configuration. Using synthetic Hamiltonians with controllable spectral properties, we show that machine-learned models can map a Hamiltonian directly to the best-ranked configuration within a predefined grid for the SKQD algorithm, validated against classical Krylov propagation, achieving strong rank correlations between true and predicted error and runtime, Spearman and , respectively. Extending the approach to 50 molecular Hamiltonians (20-50 qubits), with reference ground-state energies from classical calculations, we train regressors that predict the simulation error and runtime for a given molecule--configuration pair ahead of execution, and classifiers to distinguish, from 600 SqDRIFT quantum-hardware runs, whether a configuration achieves a ground-state energy within chemical accuracy ( Ha kcal/mol). For the molecular Hamiltonians, the models additionally provide an a priori feasibility and resource estimate, predicting whether a molecule can reach chemical accuracy on current hardware and at what runtime, thus correctly classifying held-out molecules at the molecule level, achieving balanced accuracy 61.8% in-distribution and 100% for five larger held-out molecules.
Figures & tables
| Feature set | Composition | Dimension | Estimator |
|---|---|---|---|
| Baseline | , | 2 | Random forest |
| Matrix features | 130 matrix descriptors , | 132 | Random forest |
| Encoder features | PCA-50 of the 768-dim embedding , | 52 | Random forest |
| Feature set | Composition | Dim. |
| Regression — OLS, Ridge, random forest, XGBoost [ 60 ] , LightGBM [ 61 ] | ||
| Physics | 4 descriptors config | 10 |
| Emb-PCA8 | PCA-8 of the embedding config | 14 |
| Emb-full | 768 embedding dims config | 774 |
| Physics Emb-PCA8 | 4 descriptors PCA-8 config | 18 |
| Classification — logistic regression, random forest, XGBoost [ 60 ] , LightGBM [ 61 ] , RBF-SVM, OLS-CDF | ||
Appendix figures & tables12 assets
Supplementary material from the paper’s appendix.
Appendix
| Split | Idx | Class | Formula | Circuit depth | TD GS est. (Ha) | |||
|---|---|---|---|---|---|---|---|---|
| Train | 30 | Alkanes and cycloalkanes | C 4 H 8 | 16 | 22 | 32 | ||
| Train | 51 | Alkenes and dienes | C 2 H 4 | 10 | 10 | 20 | ||
| Train | 63 | Alkenes and dienes | C 5 H 8 | 16 | 22 | 32 | ||
| Train | 101 | Alkynes | C 3 H 4 | 12 | 14 | 24 | ||
| Train | 102 | Alkynes | C 4 H 6 | 14 | 18 | 28 | ||
| Train | 106 | Alkynes | C 4 H 6 | 14 | 18 | 28 |
| Median APE (%) | |||||
| Feature set | Train | Original | Transf. | ||
| Target: state-propagation error | |||||
| Baseline ( , ) | all- | 84.9 | 116.0 | 0.660 | |
| Baseline ( , ) | OOD | 68.4 | 84.7 | 0.681 | |
| Matrix features (132) | all- | 12.3 | 8.5 | 0.990 | |
| Matrix features (132) | OOD | 15.8 | 10.4 | 0.983 | |
| all- | OOD | |||||||
|---|---|---|---|---|---|---|---|---|
| Train | Test | Train | Test | |||||
| Samples | Matrices | Samples | Matrices | Samples | Matrices | Samples | Matrices | |
| 8 | 54 504 | 3 535 | 15 740 | 1 010 | 54 504 | 3 535 | 15 740 | 1 010 |
| 16 | 101 472 | 3 469 | 28 117 | 959 | 101 472 | 3 469 | 28 117 | 959 |
| 32 | 118 592 | 2 750 | 34 235 | 791 | 118 592 | 2 750 | 34 235 | 791 |
| 64 | 104 851 | 2 496 | 27 914 | 664 | 104 851 | 2 496 | 27 914 | 664 |
| median | mode | median | mode | ||
|---|---|---|---|---|---|
| 16 | 10 | 15 | 15 | 0.5 | 0.5 |
| 32 | 10 | 25 | 25 | 0.5 | 0.5 |
| 64 | 10 | 12.5 | 10 | 0.5 | 0.5 |
| 128 | 10 | 17.5 | 15, 20 | 0.5 | 0.5 |
| 256 | 10 | 25 | 25 | 0.5 | 0.5 |
| 512 | 10 | 11 | 7 | 1.0 | 1.0 |
| Group | Descriptors | # |
|---|---|---|
| Sparsity and structure | , sparsity ratio, density, smallest nonzero magnitude, bandwidth, bandwidth/ | 6 |
| Row/column occupancy | nonzeros per row (mean, std, min, max); per column (mean, std, min, max, median, , , IQR, CV) | 13 |
| Diagonal | 12 | |
| Off-diagonal (signed) | , plus mean and max of | 14 |
| Off-diagonal magnitude | 12 | |
| Off-diagonal real part | 12 |
| Config | Num. groups | Num. rand | m ( ) | Num. samples | Total samples |
|---|---|---|---|---|---|
| A1 | [15] | 1000 | [1.0, 2.0, 3.0] | 500 | 1.5M |
| A2 | [15] | 1000 | [1.0, 2.0, 3.0, 4.0] | 375 | 1.5M |
| A3 | [20] | 1000 | [1.0, 2.0, 3.0] | 500 | 1.5M |
| A4 | [20] | 1000 | [1.0, 2.0, 3.0, 4.0] | 375 | 1.5M |
| B1 | [15] | 100 | [1.0, 2.0, 3.0] | 5000 | 1.5M |
| B2 | [15] | 100 | [1.0, 2.0, 3.0, 4.0] | 3750 | 1.5M |
| FCI dimension | Recovered (median) | Coverage | |
|---|---|---|---|
| 20 | 63,504 | 61,287 | 0.97 |
| 22 | 213,444 | 167,450 | 0.78 |
| 24 | 627,264 | 305,138 | 0.49 |
| 26 | 472,286 | 0.29 | |
| 28 | 649,173 | 0.16 | |
| 30 | 665,982 | 0.07 |
| Balanced accuracy (chance ) | Spearman (null ) | ||||
| Feature set | Estimator | ID test | OOD test | ID test | OOD test |
| Physics + config | OLS | 0.727 | 0.521 | 0.730 | 0.846 |
| Ridge | N/A | N/A | 0.723 | 0.856 | |
| RF | 0.617 | 0.542 | 0.642 | 0.643 | |
| XGBoost | 0.650 | 0.528 | 0.626 | 0.774 | |
| LightGBM | 0.655 | 0.500 | 0.608 | 0.699 | |
A Hardware-Trained Generative Quantum Eigensolver for Sample-Based Quantum Diagonalization of Organotin Hydroxides up to 70 Qubits
Machine-Learned Compact Subspace Generation for Quantum Selected Configuration Interaction within Density Matrix Embedding Framework
ibm\_torino) for CHNO, R2 (ibm\_fez) for CH, and R3 (ibm\_boston) for the larger HO benchmark and the protein-ligand system. After validating on these benchmarks of increasing active-space size, we simulate the inhibitor Carmofur bound to the SARS-CoV-2 main protease (M\textsuperscript{pro}), fragmented into ten DMET impurities. Both DMET-QSCI-RBM and a DMET-SQD baseline reach chemical-potential self-consistency within four -iterations. At the converged chemical potential, DMET-QSCI-RBM lies within of DMET-FCI while accessing on average only of the symmetry-preserving configuration space, versus at for DMET-SQD, leading to a 153-fold subspace reduction. RBM-assisted expansion thus yields far more compact hardware-derived determinant spaces at equal or better accuracy, reducing classical overhead for scalable quantum embedding of biological systems on real hardware.