Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2512.06858 · Quantum Science and Technology

Physics-Informed Generative Machine Learning for Accelerated Quantum-centric Supercomputing

Chayan Patra, Dibyendu Mondal, Sonaldeep Halder, Dipanjali Halder, Mostafizur Rahaman Laskar, Richa Goel, Rahul Maitra

quant-phSubmitted Dec 7, 2025• Announced Dec 9, 2025• 13 citations• Revised Jan 19, 2026 (v3)
v1 · Dec 7, 2025v2 · Dec 20, 2025v3 · Jan 19, 2026
arXivHTMLPDF

Abstract

Quantum centric supercomputing (QCSC) framework, such as sample-based quantum diagonalization (SQD) holds immense promise toward achieving practical quantum utility to solve challenging problems. QCSC leverages quantum computers to perform the classically intractable task of sampling the dominant fermionic configurations from the Hilbert space that have substantial support to a target state, followed by Hamiltonian diagonalization on a classical processor. However, noisy quantum hardware produces erroneous samples upon measurements, making robust and efficient configuration-recovery strategies essential for a scalable QCSC pipeline. Toward this, in this work, we introduce PIGen-SQD, an efficiently designed QCSC workflow that utilizes the capability of generative machine learning (ML) along with physics-informed configuration screening via implicit low-rank tensor decompositions for accurate fermionic state reconstruction. The physics-informed pruning is based on a class of efficient perturbative measures that, in conjunction with hardware samples, provide a substantial overlap with the target state. This distribution induces an anchoring effect on the generative ML models to stochastically explore only the dominant sector of the Hilbert space for effective identification of additional important configurations in a self-consistent manner. Our numerical experiments performed on IBM Heron R2 quantum processors demonstrate this synergistic workflow produces compact, high-fidelity subspaces that substantially reduce diagonalization cost while maintaining chemical accuracy under strong electronic correlations. By embedding classical many body intuitions directly into the generative ML model, PIGen-SQD advances the robustness and scalability of QCSC algorithms, offering a promising pathway toward chemically reliable quantum simulations on utility-scale quantum hardware.

Comments
23 pages, 11 figures

Related papers

Distributed Quantum-Centric Supercomputing with Multi-Layered Generative Learning for Intermolecular Interactions

Chayan Patra, Prayas Ghosh, Adwait Patkhedkar +1 more

Quantum-centric supercomputing (QCSC) approaches, such as sample-based quantum diagonalization (SQD), combine quantum processors with high-performance computers (HPC), offering a promising route toward solving challenging electronic structure problems. However, implementation of QCSC approaches to large active space calculations is constrained by the associated number of qubits, deep quantum circuits, sampling cost, and large-scale Hamiltonian diagonalization. To overcome these limitations, we introduce a distributed QCSC framework that decomposes complex molecular problems into parallel sub-problems requiring fewer qubits, shallower circuits, and reduced shot budgets. A physically motivated, two-step aggregation scheme then reconstructs the global solution: first, a computational bit assignment strategy optimizes a cost function to appropriately map local bit indices to global ones, yielding a mapped tensor product state (MTPS); second, an inter-fragment correlation recovery module restores missing cross-fragment interactions. Herein, we employ a multi-layered generative machine learning architecture, starting with utilizing the recently proposed physics-informed generative SQD (PIGen-SQD) as a distributed QCSC solver, followed by a secondary generative module to model configuration distributions and identify dominant sectors of the global Hilbert space. For water and formamide dimers, our method achieves up to $95\%$ reduction in the diagonalization dimension while enhancing energy accuracy by an order of magnitude over conventional SQD. Furthermore, application to the water hexamer ($\mathrm{(H_2O)_6}$) cage successfully decomposes a 120-qubit problem into six 20-qubit monomeric subsystems, and stitches the monomers under a dimeric approximation, demonstrating excellent agreement with the reference classical methods.

quant-pharXiv:2610.32968•Oct 26, 2026•0 citations

Machine-Learned Compact Subspace Generation for Quantum Selected Configuration Interaction within Density Matrix Embedding Framework

Ashish Kumar Patra, Anurag K. S. V., Ruchika Bhat +3 more

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$_5$NO, R2 (\texttt{ibm\_fez}) for C$_2$H$_4$, and R3 (\texttt{ibm\_boston}) for the larger H$_2$O 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 $0.05\,\mathrm{mHa}$ of DMET-FCI while accessing on average only $0.22\%$ of the symmetry-preserving configuration space, versus $0.55\,\mathrm{mHa}$ 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.

quant-pharXiv:2607.20585•Jul 23, 2026•4 citations

Quantum Wavefunction Augmentation via Variational Autoencoders

Sonaldeep Halder, Chayan Patra, Rahul Maitra

Sample-based quantum diagonalization (SQD) has emerged as a promising route for quantum-centric supercomputing, relying on classical diagonalization of the molecular Hamiltonian within a hardware-sampled determinant subspace. However, its accuracy degrades in strongly correlated regimes where the relevant determinant space exceeds what finite-shot sampling can capture. In this work, we introduce Quantum Wavefunction Augmentation via Variational Autoencoders (Q-WAVE), a hybrid method that combines determinants sampled via SqDRIFT Krylov circuits and configuration interaction singles and doubles (CISD) determinants with generative machine learning. Using a custom $β$-annealed variational autoencoder (VAE) model, Q-WAVE iteratively expands this basis toward the variational ground state. The VAE learns the wavefunction's primary support structure from the combined hardware and CISD seed in a continuous latent space, generating new dominant determinants beyond any fixed excitation hierarchy. The resulting compact wavefunction exceeds what can be extracted from raw hardware samples alone. We demonstrate sub-millihartree accuracy compared to full configuration interaction for $\text{H}_2\text{O}$ and $\text{N}_2$ dissociation. Finally, we establish Q-WAVE's scalability on a 52-qubit ethylene system (achieving sub-millihartree accuracy versus CCSD(T)) and a highly correlated 60-qubit $\text{Cr}_2$ stress test that attains chemical accuracy upon a final perturbative correction.

quant-pharXiv:2609.07972•Sep 9, 2026•1 citation

DF-SQD: Deterministic Fields for Sampling-Based Quantum Diagonalization

Kushagra Agarwal, Anupama Ray

Sampling-based quantum diagonalization method exploits Quantum-centric supercomputing platforms to sample bitstrings for Hamiltonian projection on a quantum computer, and then classically diagonalize the Hamiltonian to estimate the eigenvalues and eigenvectors. In current quantum devices an algorithm is useful when shallow quantum circuits with error mitigation support can discover better results while having either a proof of convergence or some method to explain trust in experiment. In this paper, we introduce DF-SQD, a hybrid algorithm that derives deterministic auxiliary-field circuits from selected double-factorization leaves of the two-electron tensor. The circuits propose occupation-number configurations, while selected configuration interaction evaluates the original active-space Hamiltonian and can recentre subsequent proposal rounds. On N2 (32 qubits; 6-31G basis) and a 40-qubit [Fe2S2(SCH3)4]2- active-space Hamiltonian, we show that DF-SQD improves the energy obtained from sampled determinant spaces while using shallow number-preserving circuits in both simulator and hardware runs. For N2, DF-SQD is 45x more accurate with a 11.23\% smaller subspace, and due to its ability to sample better bitstrings at lesser shots it is 2.93x faster than SQD in quantum devices. For the iron-sulfur cluster, DF-SQD generated a subspace dimension of 221M with 400K shots, while SQD needed 1.5M shots to generate a 238M subspace, thus we have better subspace recovery evident from the hardware at 3.75x reduced shots. At a matched 50M subspace dimension, DF-SQD is 1.32x more accurate (achieves a 24.5\% relative error reduction over standard SQD). So overall, our method is able to discover better results with shallower circuits, is sample efficient, uses configuration recovery (so has targeted error mitigation) and we have empirical convergence observation.

quant-pharXiv:2609.01264•Sep 2, 2026•0 citations

Scaling Sample-Based Quantum Diagonalization on GPU-Accelerated Systems using OpenMP Offload

Robert E. Walkup, Juha Jäykkä, Igor Pasichnyk +14 more

Hybrid quantum-HPC algorithms advance research by delegating complex tasks to quantum processors and using HPC systems to orchestrate workflows and complementary computations. Sample-based quantum diagonalization (SQD) is a hybrid quantum-HPC method in which information from a molecular Hamiltonian is encoded into a quantum circuit for evaluation on a quantum computer. A set of measurements on the quantum computer yields electronic configurations that are filtered on the classical computer, which also performs diagonalization on the selected subspace and identifies configurations to be carried over to the next step in an iterative process. Diagonalization is the most demanding task for the classical computer. Previous studies used the Fugaku supercomputer and a highly scalable diagonalization code designed for CPUs. In this work, we describe our efforts to enable efficient scalable and portable diagonalization on heterogeneous systems using GPUs as the main compute engines based on the previous work. GPUs provide massive on-device thread-level parallelism that is well aligned with the algorithms used for diagonalization. We focus on the computation of ground-state energies and wavefunctions using the Davidson algorithm with a selected set of electron configurations. We describe the offload strategy, code transformations, and data-movement, with examples of measurements on the Frontier supercomputer and five other GPU accelerated systems. Our measurements show that GPUs provide an outstanding performance boost of order 100x on a per-node basis. This dramatically expedites the diagonalization step-essential for extracting ground and excited state energies-bringing the classical processing time down from hours to minutes.

arXiv:2601.16169•Jan 22, 2026•7 citations

TGen-SQD: Physics-Informed Transferable Configuration Generator for Sample-Based Quantum Diagonalization

Niloy Deb Roy Mishu, Lei Jiang, Mohsen Heidari +2 more

Sample-based quantum diagonalization (SQD) avoids iterative variational circuit optimization, but its accuracy and cost depend on selecting a compact determinant subspace that captures the ground state. Existing machine-learning selectors use task-specific physical cues and typically retrain for each Hamiltonian. We introduce TGen-SQD, a physics-informed generator jointly trained across multiple Hamiltonians. It learns from configuration-interaction-weighted data and uses orbital- and system-level descriptors to guide generation. After training, its weights remain frozen for inference on seen and zero-shot geometries. On a 20-qubit H10 chain, TGen-SQD achieves mean energy errors of 40.18 +/- 1.52 and 43.97 +/- 1.20 mHa on seen and unseen geometries, respectively, 12.7% and 11.7% lower than the state-of-the-art PIGen-SQD baseline under matched shot and proposal budgets.

arXiv:2611.16080•Nov 11, 2026•0 citations
Quantum centric supercomputing (QCSC) framework, such as sample-based quantum diagonalization (SQD) holds immense promise toward achieving practical quantum utility to solve challenging problems. QCSC leverages quantum computers to perform the classically intractable task of sampling the dominant fermionic configurations from the Hilbert space that have substantial support to a target state, followed by Hamiltonian diagonalization on a classical processor. However, noisy quantum hardware produces erroneous samples upon measurements, making robust and efficient configuration-recovery strategies essential for a scalable QCSC pipeline. Toward this, in this work, we introduce PIGen-SQD, an efficiently designed QCSC workflow that utilizes the capability of generative machine learning (ML) along with physics-informed configuration screening via implicit low-rank tensor decompositions for accurate fermionic state reconstruction. The physics-informed pruning is based on a class of efficient perturbative measures that, in conjunction with hardware samples, provide a substantial overlap with the target state. This distribution induces an anchoring effect on the generative ML models to stochastically explore only the dominant sector of the Hilbert space for effective identification of additional important configurations in a self-consistent manner. Our numerical experiments performed on IBM Heron R2 quantum processors demonstrate this synergistic workflow produces compact, high-fidelity subspaces that substantially reduce diagonalization cost while maintaining chemical accuracy under strong electronic correlations. By embedding classical many body intuitions directly into the generative ML model, PIGen-SQD advances the robustness and scalability of QCSC algorithms, offering a promising pathway toward chemically reliable quantum simulations on utility-scale quantum hardware.
Quantum-centric supercomputing (QCSC) approaches, such as sample-based quantum diagonalization (SQD), combine quantum processors with high-performance computers (HPC), offering a promising route toward solving challenging electronic structure problems. However, implementation of QCSC approaches to large active space calculations is constrained by the associated number of qubits, deep quantum circuits, sampling cost, and large-scale Hamiltonian diagonalization. To overcome these limitations, we introduce a distributed QCSC framework that decomposes complex molecular problems into parallel sub-problems requiring fewer qubits, shallower circuits, and reduced shot budgets. A physically motivated, two-step aggregation scheme then reconstructs the global solution: first, a computational bit assignment strategy optimizes a cost function to appropriately map local bit indices to global ones, yielding a mapped tensor product state (MTPS); second, an inter-fragment correlation recovery module restores missing cross-fragment interactions. Herein, we employ a multi-layered generative machine learning architecture, starting with utilizing the recently proposed physics-informed generative SQD (PIGen-SQD) as a distributed QCSC solver, followed by a secondary generative module to model configuration distributions and identify dominant sectors of the global Hilbert space. For water and formamide dimers, our method achieves up to 95%95\%95% reduction in the diagonalization dimension while enhancing energy accuracy by an order of magnitude over conventional SQD. Furthermore, application to the water hexamer ((H2O)6\mathrm{(H_2O)_6}(H2​O)6​) cage successfully decomposes a 120-qubit problem into six 20-qubit monomeric subsystems, and stitches the monomers under a dimeric approximation, demonstrating excellent agreement with the reference classical methods.
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 CH5_55​NO, R2 (\texttt{ibm\_fez}) for C2_22​H4_44​, and R3 (\texttt{ibm\_boston}) for the larger H2_22​O 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 μμμ-iterations. At the converged chemical potential, DMET-QSCI-RBM lies within 0.05 mHa0.05\,\mathrm{mHa}0.05mHa of DMET-FCI while accessing on average only 0.22%0.22\%0.22% of the symmetry-preserving configuration space, versus 0.55 mHa0.55\,\mathrm{mHa}0.55mHa at 33.0%33.0\%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.
Sample-based quantum diagonalization (SQD) has emerged as a promising route for quantum-centric supercomputing, relying on classical diagonalization of the molecular Hamiltonian within a hardware-sampled determinant subspace. However, its accuracy degrades in strongly correlated regimes where the relevant determinant space exceeds what finite-shot sampling can capture. In this work, we introduce Quantum Wavefunction Augmentation via Variational Autoencoders (Q-WAVE), a hybrid method that combines determinants sampled via SqDRIFT Krylov circuits and configuration interaction singles and doubles (CISD) determinants with generative machine learning. Using a custom βββ-annealed variational autoencoder (VAE) model, Q-WAVE iteratively expands this basis toward the variational ground state. The VAE learns the wavefunction's primary support structure from the combined hardware and CISD seed in a continuous latent space, generating new dominant determinants beyond any fixed excitation hierarchy. The resulting compact wavefunction exceeds what can be extracted from raw hardware samples alone. We demonstrate sub-millihartree accuracy compared to full configuration interaction for H2O\text{H}_2\text{O}H2​O and N2\text{N}_2N2​ dissociation. Finally, we establish Q-WAVE's scalability on a 52-qubit ethylene system (achieving sub-millihartree accuracy versus CCSD(T)) and a highly correlated 60-qubit Cr2\text{Cr}_2Cr2​ stress test that attains chemical accuracy upon a final perturbative correction.
Sampling-based quantum diagonalization method exploits Quantum-centric supercomputing platforms to sample bitstrings for Hamiltonian projection on a quantum computer, and then classically diagonalize the Hamiltonian to estimate the eigenvalues and eigenvectors. In current quantum devices an algorithm is useful when shallow quantum circuits with error mitigation support can discover better results while having either a proof of convergence or some method to explain trust in experiment. In this paper, we introduce DF-SQD, a hybrid algorithm that derives deterministic auxiliary-field circuits from selected double-factorization leaves of the two-electron tensor. The circuits propose occupation-number configurations, while selected configuration interaction evaluates the original active-space Hamiltonian and can recentre subsequent proposal rounds. On N2 (32 qubits; 6-31G basis) and a 40-qubit [Fe2S2(SCH3)4]2- active-space Hamiltonian, we show that DF-SQD improves the energy obtained from sampled determinant spaces while using shallow number-preserving circuits in both simulator and hardware runs. For N2, DF-SQD is 45x more accurate with a 11.23\% smaller subspace, and due to its ability to sample better bitstrings at lesser shots it is 2.93x faster than SQD in quantum devices. For the iron-sulfur cluster, DF-SQD generated a subspace dimension of 221M with 400K shots, while SQD needed 1.5M shots to generate a 238M subspace, thus we have better subspace recovery evident from the hardware at 3.75x reduced shots. At a matched 50M subspace dimension, DF-SQD is 1.32x more accurate (achieves a 24.5\% relative error reduction over standard SQD). So overall, our method is able to discover better results with shallower circuits, is sample efficient, uses configuration recovery (so has targeted error mitigation) and we have empirical convergence observation.
Hybrid quantum-HPC algorithms advance research by delegating complex tasks to quantum processors and using HPC systems to orchestrate workflows and complementary computations. Sample-based quantum diagonalization (SQD) is a hybrid quantum-HPC method in which information from a molecular Hamiltonian is encoded into a quantum circuit for evaluation on a quantum computer. A set of measurements on the quantum computer yields electronic configurations that are filtered on the classical computer, which also performs diagonalization on the selected subspace and identifies configurations to be carried over to the next step in an iterative process. Diagonalization is the most demanding task for the classical computer. Previous studies used the Fugaku supercomputer and a highly scalable diagonalization code designed for CPUs. In this work, we describe our efforts to enable efficient scalable and portable diagonalization on heterogeneous systems using GPUs as the main compute engines based on the previous work. GPUs provide massive on-device thread-level parallelism that is well aligned with the algorithms used for diagonalization. We focus on the computation of ground-state energies and wavefunctions using the Davidson algorithm with a selected set of electron configurations. We describe the offload strategy, code transformations, and data-movement, with examples of measurements on the Frontier supercomputer and five other GPU accelerated systems. Our measurements show that GPUs provide an outstanding performance boost of order 100x on a per-node basis. This dramatically expedites the diagonalization step-essential for extracting ground and excited state energies-bringing the classical processing time down from hours to minutes.
Sample-based quantum diagonalization (SQD) avoids iterative variational circuit optimization, but its accuracy and cost depend on selecting a compact determinant subspace that captures the ground state. Existing machine-learning selectors use task-specific physical cues and typically retrain for each Hamiltonian. We introduce TGen-SQD, a physics-informed generator jointly trained across multiple Hamiltonians. It learns from configuration-interaction-weighted data and uses orbital- and system-level descriptors to guide generation. After training, its weights remain frozen for inference on seen and zero-shot geometries. On a 20-qubit H10 chain, TGen-SQD achieves mean energy errors of 40.18 +/- 1.52 and 43.97 +/- 1.20 mHa on seen and unseen geometries, respectively, 12.7% and 11.7% lower than the state-of-the-art PIGen-SQD baseline under matched shot and proposal budgets.