Quick design of feasible tensor networks for constrained combinatorial optimization

Abstract: In this study, we propose a new method for constrained combinatorial optimization using tensor networks. Combinatorial optimization methods employing quantum gates, such as quantum approximate optimization algorithm, have been intensively investigated. However, their limitations in errors and the number of qubits prevent them from handling large-scale combinatorial optimization problems. Alternatively, attempts have been made to solve larger-scale problems using tensor networks that can approximately simulate quantum states. In recent years, tensor networks have been applied to constrained combinatorial optimization problems for practical applications. By preparing a specific tensor network to sample states that satisfy constraints, feasible solutions can be searched for without the method of penalty functions. Previous studies have been based on profound physics, such as U(1) gauge schemes and high-dimensional lattice models. In this study, we devise to design feasible tensor networks using elementary mathematics without such a specific knowledge. One approach is to construct tensor networks with nilpotent-matrix manipulation. The second is to algebraically determine tensor parameters. For the principle verification of the proposed method, we constructed a feasible tensor network for facility location problem and conducted imaginary time evolution. We found that feasible solutions were obtained during the evolution, ultimately leading to the optimal solution. The proposed method is expected to facilitate the discovery of feasible tensor networks for constrained combinatorial optimization problems.