Neural Quantum States in Mixed Precision
quant-ph, cond-mat.str-el, cs.LG
Submitted: 2026-01-28
Updated: 2026-01-28
Comments: 22 pages, 12 figures
Journal ref: Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:114287-114310, 2026
Code: https://github.com/msolinas28/Neural_Quantum_
License: http://creativecommons.org/licenses/by/4.0/
The gist: Scientific computing has long relied on double precision (64-bit floating point) arithmetic to guarantee accuracy in simulations of real-world phenomena.
Terminology
Abstract
Scientific computing has long relied on double precision (64-bit floating point) arithmetic to guarantee accuracy in simulations of real-world phenomena. However, the growing availability of hardware accelerators such as Graphics Processing Units (GPUs) has made low-precision formats attractive due to their superior performance, reduced memory footprint, and improved energy efficiency. In this work, we investigate the role of mixed-precision arithmetic in neural-network based Variational Monte Carlo (VMC), a widely used method for solving computationally otherwise intractable quantum many-body systems. We first derive general analytical bounds on the error introduced by reduced precision on Metropolis-Hastings MCMC, and then empirically validate these bounds on the use-case of VMC. We demonstrate that significant portions of the algorithm, in particular, sampling the quantum state, can be executed in half precision without loss of accuracy. More broadly, this work provides a theoretical framework to assess the applicability of mixed-precision arithmetic in machine-learning approaches that rely on MCMC sampling. In the context of VMC, we additionally demonstrate the practical effectiveness of mixed-precision strategies, enabling more scalable and energy-efficient simulations of quantum many-body systems.
Sources
- Mixed-precision numerics in scientific applications: survey and perspectives
- Running Markov Chain Monte Carlo on Modern Hardware and Software
- Optimal approximating Markov chains for Bayesian inference
- Coupling and Decoupling to bound an approximating Markov Chain
- Coupled MCMC with a randomized acceptance probability
- Superconductivity in the two-dimensional Hubbard model revealed by neural quantum states
- Connectivity determines the capability of sparse neural network quantum states
Related papers
- Computational regimes in matrix-product-state-based quantum trajectory simulations
- Toward chemically accurate quantum simulations on quantum hardware: A quantum-HPC hybrid approach
- Transversal surface-code game with reconfigurable qubits
- Fulqrum: a generalized framework for quantum subspace diagonalization
- Flux-Activated Resonant Control of a Bosonic Quantum Memory
- Machine learning the effects of many quantum measurements