Generative machine learning models like the Restricted Boltzmann Machine (RBM) provide a practical approach for ansatz construction within the quantum computing framework. This work introduces a method that efficiently leverages RBM and many-body perturbative measures to build a compact chemistry-inspired ansatz for determining accurate molecular energetics. By training on low-rank determinants derived from an approximate wave function, RBM predicts the key high-rank determinants that dominate the ground-state wave function. A shallow depth ansatz is constructed to explicitly incorporate these dominant determinants after dynamically decomposing them into low-rank components and applying many-body perturbative measures for further screening. The method requires no additional measurements beyond the initial training phase. Moreover, it incorporates Bayesian hyperparameter optimization for the RBM, ensuring efficient performance with minimal training data during its limited usage. This approach facilitates the efficient computation of molecular properties, paving the way for exploring new chemical phenomena with near-term quantum computers.
We present a novel quantum generative framework based on Quantum Long Short-Term Memory (QLSTM) networks to optimize the sampling of Slater determinants in Full Configuration Interaction (FCI), a key method in quantum chemistry for solving the Schrödinger equation. Our model employs variational quantum circuits to learn an approximate distribution over the configuration space, guiding the generation of new, physically meaningful determinants. This distribution reflects the correlations among significant electronic configurations, allowing for a guided exploration of the determinant space and accelerating convergence toward reference energies. By framing determinant selection as a generative modeling task, our approach contributes to the emerging field of quantum generative AI applied to many-body systems. Implemented using Pennylane and accelerated with JAX, the QLSTM model converges faster than both classical LSTM and random baselines. Notably, it exhibits stable and consistent convergence across different hyperparameter settings, suggesting that the model captures an underlying physical structure rather than overfitting to specific training conditions. Our results demonstrate the scalability and physical consistency of hybrid quantum-classical generative models for quantum chemistry tasks.
Selected configuration interaction methods achieve near-exact electronic structure calculations by iteratively constructing compact variational spaces, but their efficiency depends critically on the heuristics used to identify important determinants. Here, we introduce a data-driven selection framework that recasts determinant importance as a binary classification task and integrates a neural-network classifier into the iterative CI workflow through an active-learning loop. At each iteration, a random subset of candidate determinants is labelled via temporary diagonalisation, and the trained classifier guides selection of the remaining configurations. We demonstrate the utility of this framework for both classical and quantum CI methods by calculating the ground-state energy of a diatomic molecule. Our method achieves result parity with traditional configuration interaction methods at substantially lower computational cost: roughly a
×5 reduction in memory and per-iteration cost for the classical cHCI variant, and convergence in markedly fewer iterations for the quantum-classical cSQD variant. These results establish classifier-assisted determinant selection as a lightweight, method-agnostic tool for compressing variational spaces and accelerating both classical and hybrid quantum-classical configuration interaction algorithms.
Directly solving the full electron-nuclear Schrödinger equation remains one of the grand challenges in quantum mechanics. Here, we propose a quantum-chemically motivated orbital-based neural network wavefunction ansatz with explicit many-body electron-electron correlation terms, with parameters depending on the entire electron-nuclear configuration, enabling an accurate description of strongly correlated and/or multi-reference electronic structures by a single Slater-determinant across a broad nuclear configuration space. To train this wavefunction, we further develop an efficient hybrid optimization strategy that combines the variational Monte Carlo technique with local-energy constraints, mitigating the intrinsic sampling bias of the former and considerably reducing the statistical error. These advances are embedded in a unified neural network framework, Schrödinger, enabling the determination of globally accurate potential energy surfaces with a single training for systems ranging from strongly correlated diatomic molecules, triatomic reactions containing conical intersections, to polyatomic multi-reference molecules. This work offers a practical machine-learning tool for solving the electron-nuclear Schrödinger equation and capturing full quantum effects beyond the Born-Oppenheimer approximation.
Quantum many-body calculations are fundamentally limited by the exponential growth of the configuration space, making accurate treatment of strongly correlated systems computationally prohibitive. Here we present the Generative Transformer Neural Network Selected Configuration Interaction (GTNN-SCI), a Transformer-based machine learning approach that generatively samples important configurations to accelerate many-body quantum chemistry calculations. By leveraging the Transformer architecture’s self-attention mechanism to capture long-range electron correlations, GTNN-SCI achieves up to 10× speedup compared to state-of-the-art neural network methods while maintaining high accuracy. We demonstrate the efficacy of GTNN-SCI by calculating correlation and binding energies for representative molecules including N 2, H 2 O, and C 2 using both Gaussian (cc-pVDZ) and plane-wave basis sets, achieving faster convergence and lower energies than previously reported neural network-based selected CI techniques. Most significantly, our generative approach identifies higher-order excitations missed by conventional coupling schemes, yielding lower variational energies than established methods including heat-bath CI. This capability enables GTNN-SCI to accurately treat the strongly correlated [Fe 2 S 2 (SCH 3 ) 4 ] 2– ([2Fe–2S]) cluster system, achieving ground-state energies within chemical accuracy of DMRG benchmarks, whereas conventional selected CI methods have failed on this system. The GTNN-SCI method thus combines modern deep learning with high-performance electronic structure computation, providing an efficient and precise avenue for solving the electronic Schrödinger equation in challenging molecular systems.
Sample-based quantum diagonalization (SQD), an extension of quantum selected configuration interaction (QSCI), is a promising hybrid quantum-classical paradigm for molecular ground-state energies. By replacing variational optimization with quantum sampling, QSCI avoids barren plateaus and directly reconstructs correlated wavefunctions. However, existing configuration recovery mainly enforces symmetry constraints without targeting the most physically relevant configurations, often yielding oversized subspaces and costly classical diagonalization. We introduce QSCI-RBM, a compact subspace generation protocol based on Restricted Boltzmann Machines (RBMs), and integrate it within Density Matrix Embedding Theory (DMET). The RBM learns the distribution of dominant determinants from hardware samples, generating high-probability configurations. Sampling was performed on IBM Heron R1 (\texttt{ibm\_torino}) for CH
5NO, R2 (\texttt{ibm\_fez}) for C
2H
4, and R3 (\texttt{ibm\_boston}) for the larger H
2O 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
μ-iterations. At the converged chemical potential, DMET-QSCI-RBM lies within
0.05mHa of DMET-FCI while accessing on average only
0.22% of the symmetry-preserving configuration space, versus
0.55mHa at
33.0% for DMET-SQD, leading to a $\sim$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.