Machine-learned circuit parameters could remove one of the main bottlenecks of variational quantum eigensolvers: the classical optimization loop, with its typical barren plateaus, local minima, and costly energy and gradient evaluations, is replaced by a direct prediction. Prior work showed that machine-learning models paired with a structured circuit design can transfer across system size and structure within hydrogenic systems. The next step: Extending them to organic molecules would seem to require re-training on use-case-specific training sets. In this work, we show that this is not necessary by establishing an alchemical approach. A geometric projection places surrogate hydrogen atoms along the bond directions of the target molecule and so maps its local bonding environment onto small hydrogenic fragments. Existing hydrogenic solvers can then be reused as they are. The only new quantity is a single projection radius per bond type, which is fitted once on a small reference molecule and reused unchanged thereafter. We demonstrate the approach on the separable-pair circuit designs that have been used in prior work and extend the approach to multi-circuit approaches that span effective bases for quantum subspaces.
Machine-learned circuit parameters could remove one of the main bottlenecks of variational quantum eigensolvers: the classical optimization loop, with its typical barren plateaus, local minima, and costly energy and gradient evaluations, is replaced by a direct prediction. Prior work showed that machine-learning models paired with a structured circuit design can transfer across system size and structure within hydrogenic systems. The next step: Extending them to organic molecules would seem to require re-training on use-case-specific training sets. In this work, we show that this is not necessary by establishing an alchemical approach. A geometric projection places surrogate hydrogen atoms along the bond directions of the target molecule and so maps its local bonding environment onto small hydrogenic fragments. Existing hydrogenic solvers can then be reused as they are. The only new quantity is a single projection radius per bond type, which is fitted once on a small reference molecule and reused unchanged thereafter. We demonstrate the approach on the separable-pair circuit designs that have been used in prior work and extend the approach to multi-circuit approaches that span effective bases for quantum subspaces.
The individual optimization of quantum circuit parameters is currently one of the main practical bottlenecks in variational quantum eigensolvers for electronic systems. To this end, several machine learning approaches have been proposed to mitigate the problem. However, such method predominantly aims at training and predicting parameters tailored to individual molecules: either a specific structure, or several structures of the same molecule with varying bond lengths. This work explores machine learning based modeling strategies to include transferability between different molecules. We use a well investigated quantum circuit design and apply it to model properties of hydrogenic systems where we show parameter prediction that is systematically transferable to instances significantly larger than the training instances.
Variational quantum eigensolver ansätze hold considerable promise for ground-state energy calculations on near-term quantum hardware, yet most promising ansatz designs currently strongly depend on how well the molecular orbital basis captures the electronic correlation of the system. Computing optimized orbital coefficients via classical routines is computationally expensive and must be performed independently for each molecular geometry -- a bottleneck that limits scalability across chemical space. We present a graph neural network framework that predicts optimized orbital coefficients directly from molecular geometry and pair-wise bonding structure. Trained on hydrogenic systems of modest size (H4 and H6) across tens of thousands of geometries, our model transfers to larger, unseen systems (H8, H10 and H12) without retraining -- demonstrating strong out-of-distribution generalization with respect to system size. When evaluating on structured and random configurations, and comparing against energies obtained with full classical optimization, our model reaches mean absolute energy errors O(102) and O(10) milli-Hartrees, respectively. Beyond energy estimation, the predicted orbitals serve as high-quality warm-start initializations that substantially reduce optimizer iterations to ground-state energy convergence. These results establish graph neural networks as an effective and scalable strategy for accelerating orbital optimization in hybrid quantum-classical workflows, directly reducing the classical pre-processing overhead that currently limits the practical deployment of variational quantum eigensolver on near-term quantum hardware.
Although the variational quantum eigensolver is a typical quantum algorithm utilized in near-term quantum devices, many measurements are required in an iterative closed feedback loop between the classical and quantum computers to obtain sufficient accuracy. In this study, we attempt to construct a quantum circuit learning model to infer potential energy surfaces and atomic forces without using the iterative loop to optimize parameters for every bond length. To realize a high, accurate inference performance, measurement is introduced in the middle of the circuit. When the proposed quantum circuit learning model is applied to the H2 molecule, the energies and atomic forces can be estimated with high accuracy in a single feed-forward calculation with varying bond lengths. A nonlinear relation between outcomes from data-encoding layer and inputs can also be used to eliminate the data-encoding layer, allowing for our quantum circuit model with lower learning costs by reducing the number of parameters to be optimized. Our model can be also extended to six-qubit systems, such as the H3 molecule, and to the water molecule with two internal degrees of freedom. Finally, we use the IBM Quantum backend to perform inference with a real quantum computer and show the effect of noise on the actual quantum device.
Accurate and efficient prediction of electronic wavefunctions is central to ab initio molecular dynamics (AIMD) and electronic structure theory. However, conventional ab initio methods require self-consistent optimization of electronic states at every nuclear configuration, leading to prohibitive computational costs, especially for large or strongly correlated systems. Here, we introduce a quantum-centric machine learning (QCML) model-a hybrid quantum-classical framework that integrates parameterized quantum circuits (PQCs) with Transformer-based machine learning to directly predict molecular wavefunctions and quantum observables. By pretraining the Transformer on a diverse dataset of molecules and ansatz types and subsequently fine-tuning it for specific systems, QCML learns transferable mappings between molecular descriptors and PQC parameters, eliminating the need for iterative variational optimization. The pretrained model achieves chemical accuracy in potential energy surfaces, atomic forces, and dipole moments across multiple molecules and ansatzes, and enables efficient AIMD simulations with infrared spectra prediction. This work establishes a scalable and transferable quantum-centric machine learning paradigm, bridging variational quantum algorithms and modern deep learning for next-generation molecular simulation and quantum chemistry applications.
Abstract The variational quantum Eigensolver (VQE) provides a scalable route to molecular ground-state energies on near-term quantum hardware, but its accuracy degrades rapidly as system size grows because hardware-efficient ansätze cannot span the full correlation subspace. We introduce a physics-informed ridge regression correction that is trained on the difference between VQE and Hartree–Fock (HF) energies and applied as a postprocessing step requiring no additional quantum resources. The feature set─the VQE–HF energy gap ΔE, its square ΔE2, the active-space qubit count, the number of active electrons, and two cross-term interactions─captures the dominant drivers of ansatz error in a low-dimensional, interpretable form. The model is benchmarked on H2, H2O, NH3, CH4, C2H6, and CH3OH using the STO-3G basis set and a state vector VQE simulator using a two-layer Ry-CNOT hardware-efficient ansatz. To assess cross-molecule generalizability, the corrected framework is further tested on CO2, N2, and HCN under both untrained and trained conditions. Absolute energy errors fall from a range of 0.02–0.79 Ha (raw VQE) to 0.0007–0.094 Ha after correction, corresponding to improvement factors of 3× to 640× relative to CASCI reference values. Zero-shot generalization tests yield factors of 9–58×, and including molecules in training improves results by a further order of magnitude in several cases. The three extended molecules exhibit improvement factors of 4–6× in untrained settings and 5–6× after training, providing preliminary evidence of transferability across chemically distinct systems. These findings suggest that the VQE–HF energy gap encodes physically transferable information about correlation-energy saturation, and that even the smallest training set can produce practically useful corrections for near-term quantum chemistry.
Abstract Variational quantum eigensolvers (VQEs) represent a powerful class of hybrid quantum-classical algorithms for computing molecular energies. Various numerical issues exist for these methods, however, including barren plateaus and large numbers of local minima. In this work, we consider the Adaptive, Problem-Tailored Variational Quantum Eiegensolver (ADAPT-VQE) ansätze, and examine how they are impacted by these local minima. We find that while ADAPT-VQE does not remove local minima, the gradient-informed, one-operator-at-a-time circuit construction accomplishes two things: First, it provides an initialization strategy that can yield solutions with over an order of magnitude smaller error compared to random initialization, and which is applicable in situations where chemical intuition cannot help with initialization, i.e., when Hartree-Fock is a poor approximation to the ground state. Second, even if an ADAPT-VQE iteration converges to a local trap at one step, it can still “burrow” toward the exact solution by adding more operators, which preferentially deepens the occupied trap. This same mechanism helps highlight a surprising feature of ADAPT-VQE: It should not suffer optimization problems due to barren plateaus and random initialization. Even if such barren plateaus appear in the parameter landscape, our analysis suggests that ADAPT-VQE avoids such regions by design.