SYNERGY OF QUANTUM MACHINE LEARNING AND CLASSICAL OPTIMIZATION METHODS IN ROUTING PROBLEMS
Anna A. Ilmushkina, Shamil S.-M. Yaudarov, Ali Anvarovich Khalidov
This article examines the concept of synergy between quantum machine learning and classical optimization methods in the context of routing problems. The need to integrate quantum variational algorithms with classical relaxation, heuristics, and decomposition methods to ensure computational efficiency and stability is substantiated. Particular attention is paid to the role of the classical component in generating quality estimates, parameter management, and implementing post-processing of quantum samples. Prospects for the development of hybrid algorithms in the areas of scalability, reducing noise sensitivity, and improving the accuracy of solutions in complex combinatorial settings are discussed.
SOFT MEASUREMENTS AND COMPUTING•Jan 1, 2025•0 citations