Quantum Machine Learning for Optimization Problems Leveraging Quantum Computing to Speed Up Large-Scale Optimization in AI Models
Year: 2026
Type: conference-paper
Abstract: The artificial intelligence (AI) is about optimization, which is the essence of the model training, hyper parameter optimization and the high-dimensional space decision- making. Classical methods of optimization have made much progress using gradient descent and evolutionary algorithms but are sufficient in the face of scalabilibility issues in large and non-convex and combinatoric problem spaces. The recent advancement in quantum computing provides an alternative, which is promising, whereby quantum mechanical principles of superposition, entanglement, and interference are taken advantage of to speed up search and optimization. It is suggested that a hybrid quantum-classical optimization structure should be developed, including QAOA/VQE subroutines as a part of machine learning operations. The limited hardware implementation is supported by the results of simulations, which show that approximation ratios, rate of convergence, and robustness can be measured to improve tasks like Max-Cut, portfolio optimization, and feature selection
Authors: Ram Awtar, Rohitaswa Pandey
Institution: Dr. A.P.J. Abdul Kalam Technical University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Keywords: quantum machine learning, quantum optimization, hybrid quantum-classical algorithms, quantum approximate optimization algorithm, variational quantum eigensolver, combinatorial optimization, non-convex optimization, MaxCut, portfolio optimization, feature selection, hyperparameter optimization
Open Access status: hybrid
OpenAlex ID: W7213425336
