A Predictive Approach for Selecting the Best Quantum Solver for an Optimization Problem
Deborah Volpe, Nils Quetschlich, Mariagrazia Graziano, Giovanna Turvani, Robert Wille
TL;DR
The paper tackles the barrier that non-experts face when applying quantum solvers to QUBO-formulated optimization problems. It treats solver selection as a supervised learning task, builds a dataset of over 500 QUBO instances, and demonstrates that a predictive model can choose a good solver (best in >70% of cases, top-two in ~90%) while integrating into the MQT QAO framework to automate workflows. Key contributions include a formalized feature set for QUBO problems, a comparative study of multiple ML models (with Random Forest performing best), and practical strategies for scaling solver parameters with problem size. The work has practical impact by lowering the cost and effort required to explore quantum optimization, thereby broadening access to quantum-enhanced decision-making across diverse domains. The approach lays the groundwork for automated, data-driven solver selection, which could accelerate adoption as quantum hardware and simulators evolve.
Abstract
Leveraging quantum computers for optimization problems holds promise across various application domains. Nevertheless, utilizing respective quantum computing solvers requires describing the optimization problem according to the Quadratic Unconstrained Binary Optimization (QUBO) formalism and selecting a proper solver for the application of interest with a reasonable setting. Both demand significant proficiency in quantum computing, QUBO formulation, and quantum solvers, a background that usually cannot be assumed by end users who are domain experts rather than quantum computing specialists. While tools aid in QUBO formulations, support for selecting the best-solving approach remains absent. This becomes even more challenging because selecting the best solver for a problem heavily depends on the problem itself. In this work, we are accepting this challenge and propose a predictive selection approach, which aids end users in this task. To this end, the solver selection task is first formulated as a classification task that is suitable to be solved by supervised machine learning. Based on that, we then propose strategies for adjusting solver parameters based on problem size and characteristics. Experimental evaluations, considering more than 500 different QUBO problems, confirm the benefits of the proposed solution. In fact, we show that in more than 70% of the cases, the best solver is selected, and in about 90% of the problems, a solver in the top two, i.e., the best or its closest suboptimum, is selected. This exploration proves the potential of machine learning in quantum solver selection and lays the foundations for its automation, broadening access to quantum optimization for a wider range of users.