Shadow-Based Noise Fingerprinting of Simulated Quantum Noise Models

2026-07-09

AI Summary

This work addresses the challenge that existing quantum noise characterization methods, such as quantum process tomography, scale exponentially with system size and are thus impractical for routine calibration of near-term quantum processors. The authors propose a scalable noise fingerprinting approach that employs a fixed set of three-qubit probe circuits combined with randomized Pauli measurements, classical shadow tomography, and physics-informed feature engineering to construct a 279-dimensional physically meaningful feature vector. This representation effectively discriminates between similar noise channels whose signatures otherwise overlap under generic measurements. Evaluated on a dataset comprising 10 noise classes and 14,000 samples, the method achieves an accuracy of 0.8426 and a macro F1-score of 0.8437 using a random forest classifier, significantly outperforming baseline approaches while offering both scalability and practical utility for real-world quantum hardware calibration.

Abstract

Accurate noise classification is essential for operating near-term quantum processors, yet existing approaches, such as quantum process tomography, scale exponentially with system size, limiting their practicality for routine calibration. We propose a scalable noise fingerprinting pipeline that combines structured classical shadow tomography with physics-informed feature engineering to identify noise channels from a fixed set of 3-qubit probe circuits. Each sample is represented by a 279-dimensional feature vector constructed from randomized Pauli measurements and derived observables, designed to resolve physically similar noise channels that produce overlapping signatures under generic measurement sets. We evaluate three classifiers, i.e., random forest, extra trees, and a multilayer perceptron, on a dataset of 14,000 labeled samples spanning 10 noise types. The random forest classifier achieves the highest test accuracy of 0.8426 with a macro F1 score of 0.8437, outperforming both baselines. Confusion analysis reveals that many noise types are classified with high reliability, with the remaining confusions occurring between channels sharing similar physical decay mechanisms, motivating future work on richer probe states and noise parameter estimation.

Problem

• quantum noise classification
• scalable noise fingerprinting
• near-term quantum processors
• noise channel identification
• quantum process tomography

Innovation

• classical shadow tomography
• noise fingerprinting
• physics-informed feature engineering
• scalable quantum noise classification
• Pauli measurements