Pedro H. G. Lugao
Research Subjects
Pedro H. G. Lugao has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Demerson Nunes Gonçalves
Dept. of Mathematics Federal Center for Technological Education Celso Suckow da Fonseca (CEFET-RJ) Petrópolis RJ Brazil
3 shared publications - Tharso D. Fernandes
Dept. of Mathematics Federal University of Espírito Santo (UFES) Alegre ES Brazil
3 shared publications - Andrias M. M. Cordeiro
Department of Computer Engineering, CEFET-RJ, Petrópolis 25609-010, RJ, Brazil
2 shared publications - João Terêncio Dias
Dept. of Telecommunications Engineering CEFET-RJ Rio de Janeiro RJ Brazil
2 shared publications - Fernando Manuel Araújo Moreira
Military Institute of Engineering image/svg+xml
1 shared publication - João Terêncio Dias
Instituto Militar de Engenharia (IME), Rio de Janeiro 22290-270, RJ, Brazil
1 shared publication
Latest Publications
- Open Access
- 31 July 2026
- Published by MDPI AG in Quantum Reports
- Vol. 8 (3) , 73
Certified Lower Bounds and Efficient Estimation of Minimum Accuracy in Quantum Kernel Methods
The minimum accuracy heuristic provides a training-free way to evaluate quantum feature maps, but its original formulation assumes balanced datasets, requires an exhaustive Pauli-axis scan, and lacks a formal lower-bound interpretation. In this work, we generalize the metric to arbitrary binary datasets and prove that the resulting generalized minimum accuracy, denoted , is a certified lower bound on the optimal empirical accuracy achievable by linear classifiers in the same feature space. To improve scalability, we introduce Monte Carlo axis-selection strategies that estimate from random subsets of Pauli-feature axes and derive quantile-coverage guarantees for sampling high-accuracy directions. We validate the framework using exact statevector simulations of an qubit quantum feature map, corresponding to Pauli axes, over 30 independent runs on five synthetic datasets. The proposed methods sample as few as 60 axes, produce lower-bound estimates and achieve speedups of approximately to compared with exhaustive evaluation. The results support generalized minimum accuracy as a scalable and theoretically grounded tool for pre-screening quantum feature maps in simulated quantum-kernel workflows.- 31 July 2026
- Published by MDPI AG in Quantum Reports
- Vol. 8 (3) , 73
Open AccessCertified Lower Bounds and Efficient Estimation of Minimum Accuracy in Quantum Kernel Methods
The minimum accuracy heuristic provides a training-free way to evaluate quantum feature maps, but its original formulation assumes balanced datasets, requires an exhaustive Pauli-axis scan, and lacks a formal lower-bound interpretation. In this work, we generalize the metric to arbitrary binary datasets and prove that the resulting generalized minimum accuracy, denoted , is a certified lower bound on the optimal empirical accuracy achievable by linear classifiers in the same feature space. To improve scalability, we introduce Monte Carlo axis-selection strategies that estimate from random subsets of Pauli-feature axes and derive quantile-coverage guarantees for sampling high-accuracy directions. We validate the framework using exact statevector simulations of an qubit quantum feature map, corresponding to Pauli axes, over 30 independent runs on five synthetic datasets. The proposed methods sample as few as 60 axes, produce lower-bound estimates and achieve speedups of approximately to compared with exhaustive evaluation. The results support generalized minimum accuracy as a scalable and theoretically grounded tool for pre-screening quantum feature maps in simulated quantum-kernel workflows. - Open Access
Training-Free Certified Bounds for Quantum Regression: A Scalable Framework
We present a training-free, certified error bound for quantum regression derived directly from Pauli expectation values. Generalizing the heuristic of minimum accuracy from classification to regression, we evaluate axis-aligned predictors within the Pauli feature space. We formally prove that the optimal axis-aligned predictor constitutes a rigorous upper bound on the minimum training Mean Squared Error (MSE) attainable by any linear or kernel-based regressor defined on the same quantum feature map. Since computing this exact bound requires an intractable scan of the full Pauli basis, we introduce a Monte Carlo framework to efficiently estimate it using a tractable subset of measurement axes. We further provide non-asymptotic statistical guarantees to certify performance within a practical measurement budget. This method enables rapid comparison of quantum feature maps and early diagnosis of expressivity, allowing for the informed selection of architectures before deploying higher-complexity models.
Open AccessTraining-Free Certified Bounds for Quantum Regression: A Scalable Framework
We present a training-free, certified error bound for quantum regression derived directly from Pauli expectation values. Generalizing the heuristic of minimum accuracy from classification to regression, we evaluate axis-aligned predictors within the Pauli feature space. We formally prove that the optimal axis-aligned predictor constitutes a rigorous upper bound on the minimum training Mean Squared Error (MSE) attainable by any linear or kernel-based regressor defined on the same quantum feature map. Since computing this exact bound requires an intractable scan of the full Pauli basis, we introduce a Monte Carlo framework to efficiently estimate it using a tractable subset of measurement axes. We further provide non-asymptotic statistical guarantees to certify performance within a practical measurement budget. This method enables rapid comparison of quantum feature maps and early diagnosis of expressivity, allowing for the informed selection of architectures before deploying higher-complexity models.
- Open Access
Certified Lower Bounds and Efficient Estimation of Minimum Accuracy in Quantum Kernel Methods
The minimum accuracy heuristic evaluates quantum feature maps without requiring full quantum support vector machine (QSVM) training. However, the original formulation is computationally expensive, restricted to balanced datasets, and lacks theoretical backing. This work generalizes the metric to arbitrary binary datasets and formally proves it constitutes a certified lower bound on the optimal empirical accuracy of any linear classifier in the same feature space. Furthermore, we introduce Monte Carlo strategies to efficiently estimate this bound using a random subset of Pauli directions, accompanied by rigorous probabilistic guarantees. These contributions establish minimum accuracy as a scalable, theoretically sound tool for pre-screening feature maps on near-term quantum devices.
Open AccessCertified Lower Bounds and Efficient Estimation of Minimum Accuracy in Quantum Kernel Methods
The minimum accuracy heuristic evaluates quantum feature maps without requiring full quantum support vector machine (QSVM) training. However, the original formulation is computationally expensive, restricted to balanced datasets, and lacks theoretical backing. This work generalizes the metric to arbitrary binary datasets and formally proves it constitutes a certified lower bound on the optimal empirical accuracy of any linear classifier in the same feature space. Furthermore, we introduce Monte Carlo strategies to efficiently estimate this bound using a random subset of Pauli directions, accompanied by rigorous probabilistic guarantees. These contributions establish minimum accuracy as a scalable, theoretically sound tool for pre-screening feature maps on near-term quantum devices.