Quantum Computing Benchmarks (QML)

← Back to all benchmarks

Date: 2022-02-22

Name: Quantum Computing Benchmarks QML

Domain: Computational Science & AI

Focus: Quantum algorithm performance evaluation

Task Types: Circuit benchmarking, State classification

Metrics: Fidelity, Success probability

Models: IBM Q, IonQ, AQT@LBNL

AI/ML Motif: Classification

Resources

Benchmark: Visit

Datasets: PennyLane QML Benchmarks Datasets

Results: QML Benchmarks GitHub Repository (Results section)

Keywords

quantum circuits state preparation error correction

Citation

• Joseph Bowles, Shahnawaz Ahmed, and Maria Schuld. Better than classical? the subtle art of benchmarking quantum machine learning models. 2024. URL: https://arxiv.org/abs/2403.07059, arXiv:2403.07059.

@misc{bowles2024betterclassicalsubtleart,
  title={Better than classical? The subtle art of benchmarking quantum machine learning models}, 
  author={Joseph Bowles and Shahnawaz Ahmed and Maria Schuld},
  year={2024},
  eprint={2403.07059},
  archivePrefix={arXiv},
  primaryClass={quant-ph},
  url={https://arxiv.org/abs/2403.07059}, 
}

Ratings

CategoryRating

Software

4.00

Software is built upon multiple common frameworks for simulation, training, and benchmarking workflows.

Specification

3.00

No system constraints. Task clarity and dataset format are not clearly specified.

Dataset

4.00

Datasets are accessible, but not split.

Metrics

3.00

Partially defined, somewhat inferrable metrics. Unknown whether a system's performance is captured.

Reference Solution

0.00

Not provided

Documentation

5.00

Paper is available with all required information.

Average rating: 3.17/5

Radar plot

Edit: edit this entry