Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

The Journal of Supercomputing

Evolutionary-enhanced quantum supervised learning model

Anton Simen, Rodrigo Bloot, Otto Menegasso Pires, Erick Giovani Sperandio Nascimento

Published Jan 11, 2025• 3 citations
Publisher
DOI
10.1007/s11227-024-06875-3

Related papers

Supervised learning with quantum-enhanced feature spaces

Vojtěch Havlíček, Antonio D. Corcoles, Kristan Temme +4 more

arXiv:1804.11326•Nature•Mar 13, 2019•2,584 citations

Evolutionary-enhanced quantum supervised learning model

Anton Simen Albino, Rodrigo Bloot, Otto Menegasso Pires +1 more

Quantum supervised learning, utilizing variational circuits, stands out as a promising technology for NISQ devices due to its efficiency in hardware resource utilization during the creation of quantum feature maps and the implementation of hardware-efficient ansatz with trainable parameters. Despite these advantages, the training of quantum models encounters challenges, notably the barren plateau phenomenon, leading to stagnation in learning during optimization iterations. This study proposes an innovative approach: an evolutionary-enhanced ansatz-free supervised learning model. In contrast to parametrized circuits, our model employs circuits with variable topology that evolves through an elitist method, mitigating the barren plateau issue. Additionally, we introduce a novel concept, the superposition of multi-hot encodings, facilitating the treatment of multi-classification problems. Our framework successfully avoids barren plateaus, resulting in enhanced model accuracy. Comparative analysis with variational quantum classifiers from the technology's state-of-the-art reveal a substantial improvement in training efficiency and precision. Furthermore, we conduct tests on a challenging dataset class, traditionally problematic for conventional kernel machines, demonstrating a potential alternative path for achieving quantum advantage in supervised learning for NISQ era.

arXiv:2311.08081•Nov 14, 2023•0 citations

Quantum Supervised Learning

Antonio Macaluso

arXiv:2407.17161•Künstliche Intell.•Jul 19, 2024•8 citations

Quantum and evolutionary approaches to computational learning

Dan A. Ventura

•Jan 1, 1998•2 citations

Enhanced Quantum-Inspired Supervised Learning for Telecommunication Networks

Subhadeep Mondal, M Saravanan

Quantum-Inspired Supervised Learning (QISL) leverages principles from quantum mechanics to enhance classical machine learning models, offering a promising pathway to address computational bottlenecks without the need for quantum hardware. By exploiting the high-dimensional expressibility of tensor network structures and efficient optimization techniques, QISL offers reduced parameter complexity and improved scalability compared to conventional deep learning approaches. In this paper, we investigate the application of QISL to key telecommunication network challenges, specifically focusing on throughput prediction and handover optimization. We propose a hybrid architecture that integrates QISL-based tensor representations with neural networks, employing techniques such as Adaptive Cross Approximation (ACA)-based tensor decomposition for memory efficiency and optimized loss functions for stable convergence. Through extensive numerical simulations, we demonstrate that QISL significantly reduces parameter overhead while maintaining competitive or superior prediction performance, highlighting its potential as a scalable and resource-efficient alternative for 5G and Future 6G communication systems.

Computing, Communications and IoT Applications (ComComAp)•Dec 14, 2025•0 citations

Supervised Learning with Quantum Computers

Maria Schuld, Francesco Petruccione

Quantum science and technology•Jan 1, 2018•707 citations
Quantum supervised learning, utilizing variational circuits, stands out as a promising technology for NISQ devices due to its efficiency in hardware resource utilization during the creation of quantum feature maps and the implementation of hardware-efficient ansatz with trainable parameters. Despite these advantages, the training of quantum models encounters challenges, notably the barren plateau phenomenon, leading to stagnation in learning during optimization iterations. This study proposes an innovative approach: an evolutionary-enhanced ansatz-free supervised learning model. In contrast to parametrized circuits, our model employs circuits with variable topology that evolves through an elitist method, mitigating the barren plateau issue. Additionally, we introduce a novel concept, the superposition of multi-hot encodings, facilitating the treatment of multi-classification problems. Our framework successfully avoids barren plateaus, resulting in enhanced model accuracy. Comparative analysis with variational quantum classifiers from the technology's state-of-the-art reveal a substantial improvement in training efficiency and precision. Furthermore, we conduct tests on a challenging dataset class, traditionally problematic for conventional kernel machines, demonstrating a potential alternative path for achieving quantum advantage in supervised learning for NISQ era.
Quantum-Inspired Supervised Learning (QISL) leverages principles from quantum mechanics to enhance classical machine learning models, offering a promising pathway to address computational bottlenecks without the need for quantum hardware. By exploiting the high-dimensional expressibility of tensor network structures and efficient optimization techniques, QISL offers reduced parameter complexity and improved scalability compared to conventional deep learning approaches. In this paper, we investigate the application of QISL to key telecommunication network challenges, specifically focusing on throughput prediction and handover optimization. We propose a hybrid architecture that integrates QISL-based tensor representations with neural networks, employing techniques such as Adaptive Cross Approximation (ACA)-based tensor decomposition for memory efficiency and optimized loss functions for stable convergence. Through extensive numerical simulations, we demonstrate that QISL significantly reduces parameter overhead while maintaining competitive or superior prediction performance, highlighting its potential as a scalable and resource-efficient alternative for 5G and Future 6G communication systems.