Abstract The Quantum Approximate Optimization Algorithm (QAOA) stands as a hybrid classical‐quantum algorithm utilized for addressing combinatorial optimization challenges. Central to its effectiveness is the initial mixer, which is responsible for instigating the optimization process by generating the starting state. However, conventional QAOA implementations often assign equal probabilities to all solutions at the outset, potentially resulting in suboptimal performance when tackling complex combinatorial optimization problems. In this study, a novel enhancement is proposed to the QAOA, leveraging the Difference of Convex Algorithm (DCA). This method aims to refine QAOA's performance by facilitating the discovery of optimal parameters through a continuous warm‐start approach, as originally introduced by Egger et al. Through experimentation utilizing datasets from prior studies focusing on the weighted maximum cut problem, the efficacy of our proposed method is evaluated. Comparative analysis against existing methodologies reveals a significant improvement in the approximate ratio achieved by our approach.
The Quantum Approximate Optimization Algorithm (QAOA) is a promising candidate for solving combinatorial optimization problems more efficiently than classical computers. Recent studies have shown that warm-starting the standard algorithm improves the performance. In this paper we compare the performance of standard QAOA with that of warm-start QAOA in the context of portfolio optimization and investigate the warm-start approach for different problem instances. In particular, we analyze the extent to which the improved performance of warm-start QAOA is due to quantum effects, and show that the results can be reproduced or even surpassed by a purely classical preprocessing of the original problem followed by standard QAOA.
Quantum optimization algorithms, such as the Quantum Approximate Optimization Algorithm (QAOA), are emerging as promising heuristics for solving complex combinatorial problems. To improve performance, several extensions to the standard QAOA framework have been proposed in recent years. Two notable directions include: warm-starting techniques, which incorporate classical approximate solutions to guide the quantum evolution, and custom mixer Hamiltonians, such as
XYmixers, which constrain the search to feasible subspaces aligned with the structure of the problem. In this work, we propose an approach that integrates these two strategies: a warm-start initialization with an
XYmixer ansatz, enabling constraint, preserving quantum evolution biased toward high-quality classical solutions. The method begins by reformulating the combinatorial problem as a MaxCut instance, solved approximately using the Goemans-Williamson algorithm. The resulting binary solution is relaxed and used to construct a biased superposition over one-hot quantum states that preserves the Hamming weight 1, maintaining compatibility with the
XYmixers constraints. We evaluate the approach on 5-city instances of the Traveling Salesperson Problem, a canonical optimization problem frequently encountered as a subroutine in real-world route planning problems. Our method is benchmarked against both the standard
XY-mixer QAOA and a warm-start-only variant based on MaxCut relaxation. Results show that the proposed combination consistently outperforms both baselines in terms of the percentage and rank of optimal solutions, demonstrating the effectiveness of combining structured initializations with constraint-aware quantum evolution for optimization problems.