analiza aiqbench
This study proposes a novel Quantum Machine Learning (QML) architecture that leverages quantum superposition to process entire datasets in parallel, theoretically reducing loss function evaluation complexity from $O(N^2)$ to $O(N)$. Numerical simulations indicate this approach maintains classification accuracy comparable to conventional circuits while drastically cutting the number of required circuit executions per training iteration. The work highlights a significant pathway toward scalable and efficient QML implementations by integrating core quantum algorithmic principles like interference directly into the optimization loop.
Parallel Data Processing in Quantum Machine Learning
arXiv:2508.12006v2 Announce Type: replace Abstract: We propose a Quantum Machine Learning (QML) framework that applies the core design principle of quantum algorithms-superposition, oracle, and interference-to accelerate training. Building on the structural analogy between feature extraction in foundational quantum algorithms and parameter optimization in QML, we reformulate the training process to leverage quantum parallelism: all training samples are encoded into a quantum superposition, processed through a parameterized quantum circuit, and classified via an interferometer module that implements quantum interference across the dataset. This architectural reformulation reduces the theoretical complexity of loss function evaluation from $O(N^{2})$ in conventional QML training to $O(N)$, where $N$ is the dataset size. Numerical simulations on multiple binary and multi-class classification datasets (with up to $N=128$ samples) demonstrate that our method achieves classification accuracies comparable to conventional circuits while reducing the number of quantum circuit executions per cost function evaluation from $N$ to 1. This represents a near $N$-fold reduction in quantum overhead per training iteration, reducing the required circuit executions without loss of accuracy. These results highlight the potential of quantum algorithmic design principles as a scalable pathway to efficient QML implementations.
Abstract:We propose a Quantum Machine Learning (QML) framework that applies the core design principle of quantum algorithms-superposition, oracle, and interference-to accelerate training. Building on the structural analogy between feature extraction in foundational quantum algorithms and parameter optimization in QML, we reformulate the training process to leverage quantum parallelism: all training samples are encoded into a quantum superposition, processed through a parameterized quantum circuit, and classified via an interferometer module that implements quantum interference across the dataset. This architectural reformulation reduces the theoretical complexity of loss function evaluation from $O(N^{2})$ in conventional QML training to $O(N)$, where $N$ is the dataset size. Numerical simulations on multiple binary and multi-class classification datasets (with up to $N=128$ samples) demonstrate that our method achieves classification accuracies comparable to conventional circuits while reducing the number of quantum circuit executions per cost function evaluation from $N$ to 1. This represents a near $N$-fold reduction in quantum overhead per training iteration, reducing the required circuit executions without loss of accuracy. These results highlight the potential of quantum algorithmic design principles as a scalable pathway to efficient QML implementations.
arXiv:2508.12006 [quant-ph]
(or arXiv:2508.12006v2 [quant-ph] for this version)
https://doi.org/10.48550/arXiv.2508.12006 Focus to learn more arXiv-issued DOI via DataCite
Asadiyan Zargar, S., Ramezani, M., Bahrampour, A. et al. Parallel data processing in quantum machine learning. Sci Rep (2026)
https://doi.org/10.1038/s41598-026-65756-2 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 299 cuvinte
Subiecte conexe
News
Quantum Computing Report · 25 iul. 2026
Chinese Academy of Sciences’ PQFA Cuts Multimodal Model Parameters by 10×
Quantum Zeitgeist · 30 iul. 2026
WiMi’s Quantum Circuits Boost Image Recognition Efficiency
Quantum Zeitgeist · 28 mai 2026
Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
Latent Space · 8 oct. 2026