Intelligent certification for quantum simulators via machine learning

Abstract

Quantum simulation is a technology of using controllable quantum systems to study new quantum phases of matter. Certification for quantum simulators is a challenging problem whereas identification and properties estimation are two crucial approaches that can be resorted to. In this work, we propose Ab initio end-to-end machine learning certification protocol briefly named MLCP. The learning protocol is trained with a million-level size of randomized measurement samples without relying on the assistance of quantum tomography. In the light of MLCP, we can identify different types of quantum simulators to observe their distinguishability hardness. We also predict the physical properties of quantum states evolved in quantum simulators such as entanglement entropy and maximum fidelity. The impact of randomized measurement samples on the identification accuracy is analyzed to showcase the potential capability of classical machine learning on quantum simulation results. The entanglement entropy and maximum fidelity with varied subsystem partitions are also estimated with satisfactory precision. This work paves the way for large-scale intelligent certification of quantum simulators and can be extended onto an artificial intelligence center to offer easily accessible services for local quantum simulators in the noisy intermediate-size quantum (NISQ) era.