Auto-regressive Neural Quantum State Sampling for Selected Configuration Interaction

Quantum Physics [Submitted on 25 Mar 2026] Auto-regressive Neural Quantum State Sampling for Selected Configuration Interaction Shane Thompson, Daniel Gunlycke Accurate ground-state energy calculations remain a central challenge in quantum chemistry due to the exponential scaling of the many-body Hilbert space. Variational Monte Carlo and variational quantum eigensolvers offer promising ansatz optimization approaches but face limitations in convergence as well as hardware constraints. We introduce a particular Selected Configuration Interaction (SCI) algorithm that uses auto-regressive neural networks (ARNNs) to guide subspace expansion for ground-state search. Leveraging the unique properties of ARNNs, our algorithm efficiently constructs compact variational subspaces from learned ground-state statistics, which in turn accelerates convergence to the ground-state energy. Benchmarks on molecular systems demonstrate that ARNN-guided subspace expansion combines the strengths of neural-network representations and classical subspace methods, providing a scalable framework for classical and hybrid quantum-classical algorithms. Comments: 26 pages, 13 figures, 1 table Subjects: Quantum Physics (quant-ph) Cite as: arXiv:2603.24728 [quant-ph]   (or arXiv:2603.24728v1 [quant-ph] for this version)   https://doi.org/10.48550/arXiv.2603.24728 Focus to learn more Submission history From: Shane Thompson [view email] [v1] Wed, 25 Mar 2026 18:53:00 UTC (1,633 KB) Access Paper: HTML (experimental) view license Current browse context: quant-ph < prev   |   next > new | recent | 2026-03 References & Citations INSPIRE HEP NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)