Transfer Learning for Deep-Unfolded Combinatorial Optimization Solver with Quantum Annealer
This work addresses the problem of high training costs for quantum-based solvers in combinatorial optimization, enabling more efficient use of quantum annealing in practical applications, though it is incremental as it builds on existing trainable solvers.
The paper tackled the challenge of integrating quantum annealing into a trainable combinatorial optimization solver by proposing classical-quantum transfer learning, which trains parameters classically and uses them with quantum annealing, resulting in improved convergence speed and execution time over the original solver.
Quantum annealing (QA) has attracted research interest as a sampler and combinatorial optimization problem (COP) solver. A recently proposed sampling-based solver for QA significantly reduces the required number of qubits, being capable of large COPs. In relation to this, a trainable sampling-based COP solver has been proposed that optimizes its internal parameters from a dataset by using a deep learning technique called deep unfolding. Although learning the internal parameters accelerates the convergence speed, the sampler in the trainable solver is restricted to using a classical sampler owing to the training cost. In this study, to utilize QA in the trainable solver, we propose classical-quantum transfer learning, where parameters are trained classically, and the trained parameters are used in the solver with QA. The results of numerical experiments demonstrate that the trainable quantum COP solver using classical-quantum transfer learning improves convergence speed and execution time over the original solver.