mlsanityData to 7 Oct 2026

Detecting underdetermination in parameterized quantum circuits

arXiv 2504.03315 ↗First posted 4 Apr 2025quant-ph cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

A central question in machine learning is how reliable the predictions of a trained model are. Reliability includes the identification of instances for which a model is likely not to be trusted based on an analysis of the learning system itself. Such unreliability for an input may arise from the model family providing a variety of hypotheses consistent with the training data, which can vastly disagree in their predictions on that particular input point. This is called the underdetermination problem, and it is important to develop methods to detect it. With the emergence of quantum machine learning (QML) as a prospective alternative to classical methods for certain learning problems, the question arises to what extent they are subject to underdetermination and whether similar techniques as those developed for classical models can be employed for its detection. In this work, we first provide an overview of concepts from Safe AI and reliability, which in particular received little attention in QML. We then explore the use of a method based on local second-order information for the detection of underdetermination in parameterized quantum circuits through numerical experiments. We further demonstrate that the approach is robust to certain levels of shot noise. Our work contributes to the body of literature on Safe Quantum AI, which is an emerging field of growing importance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 55 of its 97 references that are in the map. First posted on arXiv 4 Apr 2025.

Builds on

55 of 97 references.

References · 55

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  4. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  5. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  6. 2022Toy Models of Superpositioncited by 928
  7. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  8. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  9. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  10. 2018Barren plateaus in quantum neural network training landscapescited by 624
  11. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 488
  12. 2020Artificial Intelligence, Values and Alignmentcited by 443
38 more
  1. 2020The effect of data encoding on the expressive power of variational quantum machine learning modelscited by 328
  2. 2020A Survey on Neural Network Interpretabilitycited by 291
  3. 2020A rigorous and robust quantum speed-up in supervised machine learningcited by 270
  4. 2023AI Alignment: A Comprehensive Surveycited by 256
  5. 2019Algorithms for Verifying Deep Neural Networkscited by 221
  6. 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunitiescited by 125
  7. 2020Secure and Robust Machine Learning for Healthcare: A Surveycited by 77
  8. 2020Quantum noise protects quantum classifiers against adversariescited by 68
  9. 2022Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisationcited by 65
  10. 2019Quantum Adversarial Machine Learningcited by 64
  11. 2019Shaping the learning landscape in neural networks around wide flat minimacited by 47
  12. 2022Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspectivecited by 41
  13. 2023On Second-Order Scoring Rules for Epistemic Uncertainty Quantificationcited by 38
  14. 2020Fairness in Learning-Based Sequential Decision Algorithms: A Surveycited by 35
  15. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  16. 2022Benchmarking Adversarially Robust Quantum Machine Learning at Scalecited by 28
  17. 2023Towards quantum enhanced adversarial robustness in machine learningcited by 26
  18. 2024On the relation between trainability and dequantization of variational quantum learning modelscited by 24
  19. 2020Optimal Provable Robustness of Quantum Classification via Quantum Hypothesis Testingcited by 23
  20. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 22
  21. 2023Exponential separations between classical and quantum learnerscited by 21
  22. 2023Training robust and generalizable quantum modelscited by 21
  23. 2020Robustness Verification of Quantum Classifierscited by 18
  24. 2022Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noisecited by 17
  25. 2023Explaining Quantum Circuits with Shapley Values: Towards Explainable Quantum Machine Learningcited by 17
  26. 2021Security and Privacy for Artificial Intelligence: Opportunities and Challengescited by 16
  27. 2022Enhancing Quantum Adversarial Robustness by Randomized Encodingscited by 16
  28. 2023Interpretability of Machine Learning: Recent Advances and Future Prospectscited by 12
  29. 2024A Comparative Analysis of Adversarial Robustness for Quantum and Classical Machine Learning Modelscited by 12
  30. 2023Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learningcited by 11
  31. 2021Statistical Perspectives on Reliability of Artificial Intelligence Systemscited by 10
  32. 2024Hyper Evidential Deep Learning to Quantify Composite Classification Uncertaintycited by 10
  33. 2020AI safety: state of the field through quantitative lenscited by 9
  34. 2024Predominant Aspects on Security for Quantum Machine Learning: Literature Reviewcited by 9
  35. 2022Study of Feature Importance for Quantum Machine Learning Modelscited by 7
  36. 2022Verifying Fairness in Quantum Machine Learningcited by 7
  37. 2023QuantumEyes: Towards Better Interpretability of Quantum Circuitscited by 6
  38. 2024Adversarial Robustness Guarantees for Quantum Classifierscited by 6

50 most cited of 55 All 55 (JSON)

Built on by

Not cited yet.