Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Machine Learning-Based Error Mitigation Approach For Reliable Software Development On IBM'S Quantum Computers

Asmar Muqeet, Shaukat Ali, Tao Yue, Paolo Arcaini

TL;DR

Quantum software reliability is hindered by device noise; this work presents Q-LEAR, an ML-based error mitigation framework with a novel Depth-cut Program Error feature to better quantify noise. It uses circuit- and output-level features derived from transpiled circuits and measured outputs, trained on IBM noise models, and evaluated against QRAFT on eight devices and simulators. Across application-level circuits, Q-LEAR’s MLP model achieves around a 25% improvement in mitigating output errors, with real hardware showing smaller gains due to stronger, less predictable noise; LOCO analysis confirms all features contribute, especially Prob_obv. The approach demonstrates practical post-processing integration with Qiskit and suggests that carefully designed features and realistic training data substantially improve reliability in near-term quantum software development.

Abstract

Quantum computers have the potential to outperform classical computers for some complex computational problems. However, current quantum computers (e.g., from IBM and Google) have inherent noise that results in errors in the outputs of quantum software executing on the quantum computers, affecting the reliability of quantum software development. The industry is increasingly interested in machine learning (ML)--based error mitigation techniques, given their scalability and practicality. However, existing ML-based techniques have limitations, such as only targeting specific noise types or specific quantum circuits. This paper proposes a practical ML-based approach, called Q-LEAR, with a novel feature set, to mitigate noise errors in quantum software outputs. We evaluated Q-LEAR on eight quantum computers and their corresponding noisy simulators, all from IBM, and compared Q-LEAR with a state-of-the-art ML-based approach taken as baseline. Results show that, compared to the baseline, Q-LEAR achieved a 25% average improvement in error mitigation on both real quantum computers and simulators. We also discuss the implications and practicality of Q-LEAR, which, we believe, is valuable for practitioners.

A Machine Learning-Based Error Mitigation Approach For Reliable Software Development On IBM'S Quantum Computers

TL;DR

Quantum software reliability is hindered by device noise; this work presents Q-LEAR, an ML-based error mitigation framework with a novel Depth-cut Program Error feature to better quantify noise. It uses circuit- and output-level features derived from transpiled circuits and measured outputs, trained on IBM noise models, and evaluated against QRAFT on eight devices and simulators. Across application-level circuits, Q-LEAR’s MLP model achieves around a 25% improvement in mitigating output errors, with real hardware showing smaller gains due to stronger, less predictable noise; LOCO analysis confirms all features contribute, especially Prob_obv. The approach demonstrates practical post-processing integration with Qiskit and suggests that carefully designed features and realistic training data substantially improve reliability in near-term quantum software development.

Abstract

Quantum computers have the potential to outperform classical computers for some complex computational problems. However, current quantum computers (e.g., from IBM and Google) have inherent noise that results in errors in the outputs of quantum software executing on the quantum computers, affecting the reliability of quantum software development. The industry is increasingly interested in machine learning (ML)--based error mitigation techniques, given their scalability and practicality. However, existing ML-based techniques have limitations, such as only targeting specific noise types or specific quantum circuits. This paper proposes a practical ML-based approach, called Q-LEAR, with a novel feature set, to mitigate noise errors in quantum software outputs. We evaluated Q-LEAR on eight quantum computers and their corresponding noisy simulators, all from IBM, and compared Q-LEAR with a state-of-the-art ML-based approach taken as baseline. Results show that, compared to the baseline, Q-LEAR achieved a 25% average improvement in error mitigation on both real quantum computers and simulators. We also discuss the implications and practicality of Q-LEAR, which, we believe, is valuable for practitioners.
Paper Structure (25 sections, 3 equations, 4 figures, 4 tables)

This paper contains 25 sections, 3 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Related Work and Their Limitations
  4. Preliminaries
  5. Output State
  6. Circuit Output
  7. Output Error
  8. Output State Error
  9. Approach
  10. Circuit-level Features
  11. Output-level Features
  12. Evaluation and Analysis
  13. Research Question
  14. Experiment Design
  15. Benchmarks
  16. ...and 10 more sections

Figures (4)

  • Figure 1: W-state quantum program
  • Figure 2: Overview of the process of calculating Q-LEAR's feature set for a given quantum circuit and quantum computer
  • Figure 3: RQ3 -- LOCO feature importance boxplots for the MLP model on test data for real computers and application-level circuits. The text (red) shows the %difference between the medians of boxplots with and without a specific feature.
  • Figure 4: Quantum Program Execution Flow using IBM's Qiskit Framework integrated with Q-LEAR