Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning
Quantum machine learning is a promising programming paradigm for the optimization of quantum algorithms in the current era of noisy intermediate-scale quantum computers. A fundamental challenge in quantum machine learning is generalization, as the designer targets performance under testing condition...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Transactions on Quantum Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10321713/ |
| _version_ | 1797302654103191552 |
|---|---|
| author | Sangwoo Park Osvaldo Simeone |
| author_facet | Sangwoo Park Osvaldo Simeone |
| author_sort | Sangwoo Park |
| collection | DOAJ |
| description | Quantum machine learning is a promising programming paradigm for the optimization of quantum algorithms in the current era of noisy intermediate-scale quantum computers. A fundamental challenge in quantum machine learning is generalization, as the designer targets performance under testing conditions while having access only to limited training data. Existing generalization analyses, while identifying important general trends and scaling laws, cannot be used to assign reliable and informative “error bars” to the decisions made by quantum models. In this article, we propose a general methodology that can reliably quantify the uncertainty of quantum models, irrespective of the amount of training data, the number of shots, the ansatz, the training algorithm, and the presence of quantum hardware noise. The approach, which builds on probabilistic conformal prediction (CP), turns an arbitrary, possibly small, number of shots from a pretrained quantum model into a set prediction, e.g., an interval, that <italic>provably</italic> contains the true target with any desired coverage level. Experimental results confirm the theoretical calibration guarantees of the proposed framework, referred to as quantum CP. |
| first_indexed | 2024-03-07T23:41:53Z |
| format | Article |
| id | doaj.art-fa98064aded04f6da16d8b44a1af9f05 |
| institution | Directory Open Access Journal |
| issn | 2689-1808 |
| language | English |
| last_indexed | 2024-03-07T23:41:53Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Quantum Engineering |
| spelling | doaj.art-fa98064aded04f6da16d8b44a1af9f052024-02-20T00:01:34ZengIEEEIEEE Transactions on Quantum Engineering2689-18082024-01-01512410.1109/TQE.2023.333322410321713Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine LearningSangwoo Park0https://orcid.org/0000-0003-4091-7860Osvaldo Simeone1https://orcid.org/0000-0001-9898-3209King's Communications, Learning and Information Processing lab, Centre for Intelligent Information Processing Systems, Department of Engineering, King's College London, London, U.K.King's Communications, Learning and Information Processing lab, Centre for Intelligent Information Processing Systems, Department of Engineering, King's College London, London, U.K.Quantum machine learning is a promising programming paradigm for the optimization of quantum algorithms in the current era of noisy intermediate-scale quantum computers. A fundamental challenge in quantum machine learning is generalization, as the designer targets performance under testing conditions while having access only to limited training data. Existing generalization analyses, while identifying important general trends and scaling laws, cannot be used to assign reliable and informative “error bars” to the decisions made by quantum models. In this article, we propose a general methodology that can reliably quantify the uncertainty of quantum models, irrespective of the amount of training data, the number of shots, the ansatz, the training algorithm, and the presence of quantum hardware noise. The approach, which builds on probabilistic conformal prediction (CP), turns an arbitrary, possibly small, number of shots from a pretrained quantum model into a set prediction, e.g., an interval, that <italic>provably</italic> contains the true target with any desired coverage level. Experimental results confirm the theoretical calibration guarantees of the proposed framework, referred to as quantum CP.https://ieeexplore.ieee.org/document/10321713/Conformal prediction (CP)generalization analysisquantum machine learninguncertainty quantification |
| spellingShingle | Sangwoo Park Osvaldo Simeone Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning IEEE Transactions on Quantum Engineering Conformal prediction (CP) generalization analysis quantum machine learning uncertainty quantification |
| title | Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning |
| title_full | Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning |
| title_fullStr | Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning |
| title_full_unstemmed | Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning |
| title_short | Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning |
| title_sort | quantum conformal prediction for reliable uncertainty quantification in quantum machine learning |
| topic | Conformal prediction (CP) generalization analysis quantum machine learning uncertainty quantification |
| url | https://ieeexplore.ieee.org/document/10321713/ |
| work_keys_str_mv | AT sangwoopark quantumconformalpredictionforreliableuncertaintyquantificationinquantummachinelearning AT osvaldosimeone quantumconformalpredictionforreliableuncertaintyquantificationinquantummachinelearning |