A deep learning model for noise prediction on near-term quantum devices

TL;DR

This paper introduces a deep learning-based compiler that predicts and mitigates noise in quantum circuits on specific hardware, leading to significant noise reduction and improved quantum operation fidelity.

Contribution

It develops a hardware-specific noise prediction model using neural networks and integrates it into a quantum circuit compiler to reduce output noise.

Findings

Achieved 12.3% noise reduction on IBM 5-qubit devices.

Noise model is highly device-specific, with only 5.2% reduction when applied across devices.

Demonstrated machine learning can enhance quantum circuit fidelity.

Abstract

We present an approach for a deep-learning compiler of quantum circuits, designed to reduce the output noise of circuits run on a specific device. We train a convolutional neural network on experimental data from a quantum device to learn a hardware-specific noise model. A compiler then uses the trained network as a noise predictor and inserts sequences of gates in circuits so as to minimize expected noise. We tested this approach on the IBM 5-qubit devices and observed a reduction in output noise of 12.3% (95% CI [11.5%, 13.0%]) compared to the circuits obtained by the Qiskit compiler. Moreover, the trained noise model is hardware-specific: applying a noise model trained on one device to another device yields a noise reduction of only 5.2% (95% CI [4.9%, 5.6%]). These results suggest that device-specific compilers using machine learning may yield higher fidelity operations and provide insights for the design of noise models.