Neural-network-assisted Monte Carlo sampling trained by Quantum Approximate Optimization Algorithm

TL;DR

This paper introduces a hybrid quantum-classical Monte Carlo method that uses a neural network trained on quantum samples to improve sampling efficiency, demonstrating significant speedups in spin glass problems on NISQ devices.

Contribution

It proposes a neural-network-assisted quantum Monte Carlo framework that overcomes circuit constraints, enabling more effective quantum sampling for practical applications.

Findings

Achieved ~100x spectral gap improvement over uniform proposals.

Maintained acceleration without parameter optimization.

Demonstrated effectiveness on spin glass Boltzmann sampling.

Abstract

Sampling problems are widely regarded as the task for which quantum computers can most readily provide a quantum advantage. Leveraging this feature, the quantum-enhanced Markov chain Monte Carlo [Layden, D. et al., Nature 619, 282-287 (2023)] has been proposed recently, where sampling from a quantum computer is used as a proposal distribution and convergence to a target distribution is accelerated. However, guaranteeing convergence to the target distribution typically forces one to impose restrictive symmetry constraints on the quantum circuit, which makes it hard to design good proposal distributions and prevents making full use of the advantage of a quantum computer. We explore a hybrid quantum-classical MCMC framework that combines a quantum circuit with a generative neural sampler (GNS). The GNS is trained on quantum samples and acts as a classical surrogate to efficiently emulate quantum outputs, thereby lifting circuit constraints. We apply this method to Boltzmann sampling of spin glasses using proposals trained with a QAOA circuit. This approach outperforms conventional methods, showing a $\sim$100$\times$ improvement in spectral gap over uniform proposals. Notably, it maintains similar acceleration even without parameter optimization. These results establish the method as a viable sampling-based quantum algorithm for NISQ devices and highlight its potential for solving practical problems with quantum computation.