arXiv:2504.10733 · IEEE International Conference on Quantum Computing and Engineering (QCE)

Cross-Problem Parameter Transfer in Quantum Approximate Optimization Algorithm: a Machine Learning Approach

Kien X. Nguyen, Bao Bach, Ilya Safro

Published Aug 30, 2025• 1 citation

Abstract

Quantum Approximate Optimization Algorithm (QAOA) is one of the most promising candidates to achieve the quantum advantage in solving combinatorial optimization problems. The process of finding a good set of variational parameters in the QAOA circuit has proven to be challenging due to multiple factors, such as barren plateaus. As a result, there is growing interest in exploiting parameter transferability, where parameter sets optimized for one problem instance are transferred to another that could be more complex either to estimate the solution or to serve as a warm start for further optimization. But can we transfer parameters from one class of problems to another? Leveraging parameter sets learned from a well-studied class of problems could help navigate the less studied one, reducing optimization overhead and mitigating performance pitfalls. In this paper, we study whether pretrained QAOA parameters of MaxCut can be used as is or to warm start the Maximum Independent Set (MIS) circuits. Specifically, we design machine learning models to find good donor candidates optimized on MaxCut and apply their parameters to MIS acceptors. Our experimental results show that such parameter transfer can significantly reduce the number of optimization iterations required while achieving comparable approximation ratios. Reproducibility: Our results and code are available at: https://github.com/Nyquixt/Cross-Problem-PT-QAOA.

DOI: 10.1109/qce65121.2025.00240

Related papers

Transfer learning of optimal QAOA parameters in combinatorial optimization

J. A. Montañez-Barrera, Dennis Willsch, Kristel F. L. Michielsen

arXiv:2402.05549Feb 8, 20243 citations

Graph representation learning for parameter transferability in quantum approximate optimization algorithm

Jose Falla, Quinn Langfitt, Yuri Alexeev +1 more

arXiv:2401.06655Quantum Machine IntelligenceJul 22, 202422 citations

Similarity-Based Parameter Transferability in the Quantum Approximate Optimization Algorithm

Alexey Galda, Eesh Gupta, Jose Falla +4 more

arXiv:2307.05420Jul 11, 20232 citations

Similarity-based parameter transferability in the quantum approximate optimization algorithm

Alexey Galda, Eesh Gupta, Jose Falla +4 more

Frontiers in Quantum Science and TechnologyJul 13, 202330 citations

Scaling QAOA: transferring optimal adiabatic schedules from small-scale to large-scale variational circuits

Ugo Nzongani, Dylan Laplace Mermoud, Arthur Braida

quant-pharXiv:2602.14986IEEE International Conference on Quantum Control, Computing and Learning (qCCL)Feb 17, 20260 citations

QAOA Parameter Transferability for Maximum Independent Set using Graph Attention Networks

Hanjing Xu, Xiaoyuan Liu, Alex Pothen +1 more

arXiv:2504.21135IEEE High Performance Extreme Computing ConferenceSep 15, 20250 citations

arXiv:2504.10733 · IEEE International Conference on Quantum Computing and Engineering (QCE)

Cross-Problem Parameter Transfer in Quantum Approximate Optimization Algorithm: a Machine Learning Approach

Kien X. Nguyen, Bao Bach, Ilya Safro

Published Aug 30, 2025• 1 citation

arXiv HTML PDF

Abstract

DOI: 10.1109/qce65121.2025.00240

Related papers

Transfer learning of optimal QAOA parameters in combinatorial optimization

J. A. Montañez-Barrera, Dennis Willsch, Kristel F. L. Michielsen

Solving combinatorial optimization problems (COPs) is a promising application of quantum computation, with the Quantum Approximate Optimization Algorithm (QAOA) being one of the most studied quantum algorithms for solving them. However, multiple factors make the parameter search of the QAOA a hard optimization problem. In this work, we study transfer learning (TL), a methodology to reuse pre-trained QAOA parameters of one problem instance into different COP instances. This methodology can be used to alleviate the necessity of classical optimization to find good parameters for individual problems. To this end, we select small cases of the traveling salesman problem (TSP), the bin packing problem (BPP), the knapsack problem (KP), the weighted maximum cut (MaxCut) problem, the maximal independent set (MIS) problem, and portfolio optimization (PO), and find optimal $β$ and $γ$ parameters for p layers. We compare how well the parameters found for one problem adapt to the others. Among the different problems, BPP is the one that produces the best transferable parameters, maintaining the probability of finding the optimal solution above a quadratic speedup over random guessing for problem sizes up to 42 qubits and p = 10 layers. Using the BPP parameters, we perform experiments on IonQ Harmony and Aria, Rigetti Aspen-M-3, and IBM Brisbane of MIS instances for up to 18 qubits. The results indicate that IonQ Aria yields the best overlap with the ideal probability distribution. Additionally, we show that cross-platform TL is possible using the D-Wave Advantage quantum annealer with the parameters found for BPP. We show an improvement in performance compared to the default protocols for MIS with up to 170 qubits. Our results suggest that there are QAOA parameters that generalize well for different COPs and annealing protocols.Solving combinatorial optimization problems (COPs) is a promising application of quantum computation, with the Quantum Approximate Optimization Algorithm (QAOA) being one of the most studied quantum algorithms for solving them. However, multiple factors make the parameter search of the QAOA a hard optimization problem. In this work, we study transfer learning (TL), a methodology to reuse pre-trained QAOA parameters of one problem instance into different COP instances. This methodology can be used to alleviate the necessity of classical optimization to find good parameters for individual problems. To this end, we select small cases of the traveling salesman problem (TSP), the bin packing problem (BPP), the knapsack problem (KP), the weighted maximum cut (MaxCut) problem, the maximal independent set (MIS) problem, and portfolio optimization (PO), and find optimal $β$ and $γ$ parameters for p layers. We compare how well the parameters found for one problem adapt to the others. Among the different problems, BPP is the one that produces the best transferable parameters, maintaining the probability of finding the optimal solution above a quadratic speedup over random guessing for problem sizes up to 42 qubits and p = 10 layers. Using the BPP parameters, we perform experiments on IonQ Harmony and Aria, Rigetti Aspen-M-3, and IBM Brisbane of MIS instances for up to 18 qubits. The results indicate that IonQ Aria yields the best overlap with the ideal probability distribution. Additionally, we show that cross-platform TL is possible using the D-Wave Advantage quantum annealer with the parameters found for BPP. We show an improvement in performance compared to the default protocols for MIS with up to 170 qubits. Our results suggest that there are QAOA parameters that generalize well for different COPs and annealing protocols.

arXiv:2402.05549Feb 8, 20243 citations

Graph representation learning for parameter transferability in quantum approximate optimization algorithm

Jose Falla, Quinn Langfitt, Yuri Alexeev +1 more

Abstract The quantum approximate optimization algorithm (QAOA) is one of the most promising candidates for achieving quantum advantage through quantum-enhanced combinatorial optimization. Optimal QAOA parameter concentration effects for special MaxCut problem instances have been observed, but a rigorous study of the subject is still lacking. Due to clustering of optimal QAOA parameters for MaxCut, successful parameter transferability between different MaxCut instances can be explained and predicted based on local properties of the graphs, including the type of subgraphs (lightcones) from which graphs are composed as well as the overall degree of nodes in the graph (parity). In this work, we apply five different graph embedding techniques to determine good donor candidates for parameter transferability, including parameter transferability between different classes of MaxCut instances. Using this technique, we effectively reduce the number of iterations required for parameter optimization, obtaining an approximate solution to the target problem with an order of magnitude speedup. This procedure also effectively removes the problem of encountering barren plateaus during the variational optimization of parameters. Additionally, our findings demonstrate that the transferred parameters maintain effectiveness when subjected to noise, supporting their use in real-world quantum applications. This work presents a framework for identifying classes of combinatorial optimization instances for which optimal donor candidates can be predicted such that QAOA can be substantially accelerated under both ideal and noisy conditions.Abstract The quantum approximate optimization algorithm (QAOA) is one of the most promising candidates for achieving quantum advantage through quantum-enhanced combinatorial optimization. Optimal QAOA parameter concentration effects for special MaxCut problem instances have been observed, but a rigorous study of the subject is still lacking. Due to clustering of optimal QAOA parameters for MaxCut, successful parameter transferability between different MaxCut instances can be explained and predicted based on local properties of the graphs, including the type of subgraphs (lightcones) from which graphs are composed as well as the overall degree of nodes in the graph (parity). In this work, we apply five different graph embedding techniques to determine good donor candidates for parameter transferability, including parameter transferability between different classes of MaxCut instances. Using this technique, we effectively reduce the number of iterations required for parameter optimization, obtaining an approximate solution to the target problem with an order of magnitude speedup. This procedure also effectively removes the problem of encountering barren plateaus during the variational optimization of parameters. Additionally, our findings demonstrate that the transferred parameters maintain effectiveness when subjected to noise, supporting their use in real-world quantum applications. This work presents a framework for identifying classes of combinatorial optimization instances for which optimal donor candidates can be predicted such that QAOA can be substantially accelerated under both ideal and noisy conditions.

arXiv:2401.06655Quantum Machine IntelligenceJul 22, 202422 citations

Similarity-Based Parameter Transferability in the Quantum Approximate Optimization Algorithm

Alexey Galda, Eesh Gupta, Jose Falla +4 more

The quantum approximate optimization algorithm (QAOA) is one of the most promising candidates for achieving quantum advantage through quantum-enhanced combinatorial optimization. A near-optimal solution to the combinatorial optimization problem is achieved by preparing a quantum state through the optimization of quantum circuit parameters. Optimal QAOA parameter concentration effects for special MaxCut problem instances have been observed, but a rigorous study of the subject is still lacking. In this work we show clustering of optimal QAOA parameters around specific values; consequently, successful transferability of parameters between different QAOA instances can be explained and predicted based on local properties of the graphs, including the type of subgraphs (lightcones) from which graphs are composed as well as the overall degree of nodes in the graph (parity). We apply this approach to several instances of random graphs with a varying number of nodes as well as parity and show that one can use optimal donor graph QAOA parameters as near-optimal parameters for larger acceptor graphs with comparable approximation ratios. This work presents a pathway to identifying classes of combinatorial optimization instances for which variational quantum algorithms such as QAOA can be substantially accelerated.The quantum approximate optimization algorithm (QAOA) is one of the most promising candidates for achieving quantum advantage through quantum-enhanced combinatorial optimization. A near-optimal solution to the combinatorial optimization problem is achieved by preparing a quantum state through the optimization of quantum circuit parameters. Optimal QAOA parameter concentration effects for special MaxCut problem instances have been observed, but a rigorous study of the subject is still lacking. In this work we show clustering of optimal QAOA parameters around specific values; consequently, successful transferability of parameters between different QAOA instances can be explained and predicted based on local properties of the graphs, including the type of subgraphs (lightcones) from which graphs are composed as well as the overall degree of nodes in the graph (parity). We apply this approach to several instances of random graphs with a varying number of nodes as well as parity and show that one can use optimal donor graph QAOA parameters as near-optimal parameters for larger acceptor graphs with comparable approximation ratios. This work presents a pathway to identifying classes of combinatorial optimization instances for which variational quantum algorithms such as QAOA can be substantially accelerated.

arXiv:2307.05420Jul 11, 20232 citations

Similarity-based parameter transferability in the quantum approximate optimization algorithm

Alexey Galda, Eesh Gupta, Jose Falla +4 more

Frontiers in Quantum Science and TechnologyJul 13, 202330 citations

Scaling QAOA: transferring optimal adiabatic schedules from small-scale to large-scale variational circuits

Ugo Nzongani, Dylan Laplace Mermoud, Arthur Braida

The Quantum Approximate Optimization Algorithm (QAOA) is a leading approach for combinatorial optimization on near-term quantum devices, yet its scalability is limited by the difficulty of optimizing $2p$ variational parameters for a large number $p$ of layers. Recent empirical studies indicate that optimal QAOA angles exhibit concentration and transferability across problem sizes. Leveraging this observation, we propose a schedule-learning framework that transfers spectral-gap-informed adiabatic control strategies from small-scale instances to larger systems. Our method extracts the spectral gap profile of small problems and constructs a continuous schedule governed by $\partial_t s = κg^q(s)$ , where $g(s)$ is the instantaneous gap and $(κ, q)$ are global hyperparameters. Discretizing this schedule yields closed-form expressions for all QAOA angles, reducing the classical optimization task from $2p$ parameters to only $2$ , independent of circuit depth. This drastic parameter compression mitigates classical optimization overhead and reduces sensitivity to barren plateau phenomena. Numerical simulations on random QUBO and 3-regular MaxCut instances demonstrate that the learnt schedules transfer effectively to larger systems while achieving competitive approximation ratios. Our results suggest that gap-informed schedule transfers provide a scalable and parameter-efficient strategy for QAOA.The Quantum Approximate Optimization Algorithm (QAOA) is a leading approach for combinatorial optimization on near-term quantum devices, yet its scalability is limited by the difficulty of optimizing $2p$ variational parameters for a large number $p$ of layers. Recent empirical studies indicate that optimal QAOA angles exhibit concentration and transferability across problem sizes. Leveraging this observation, we propose a schedule-learning framework that transfers spectral-gap-informed adiabatic control strategies from small-scale instances to larger systems. Our method extracts the spectral gap profile of small problems and constructs a continuous schedule governed by $\partial_t s = κg^q(s)$, where $g(s)$ is the instantaneous gap and $(κ, q)$ are global hyperparameters. Discretizing this schedule yields closed-form expressions for all QAOA angles, reducing the classical optimization task from $2p$ parameters to only $2$, independent of circuit depth. This drastic parameter compression mitigates classical optimization overhead and reduces sensitivity to barren plateau phenomena. Numerical simulations on random QUBO and 3-regular MaxCut instances demonstrate that the learnt schedules transfer effectively to larger systems while achieving competitive approximation ratios. Our results suggest that gap-informed schedule transfers provide a scalable and parameter-efficient strategy for QAOA.

quant-pharXiv:2602.14986IEEE International Conference on Quantum Control, Computing and Learning (qCCL)Feb 17, 20260 citations

QAOA Parameter Transferability for Maximum Independent Set using Graph Attention Networks

Hanjing Xu, Xiaoyuan Liu, Alex Pothen +1 more

The quantum approximate optimization algorithm (QAOA) is one of the promising variational approaches of quantum computing to solve combinatorial optimization problems. In QAOA, variational parameters need to be optimized by solving a series of nonlinear, nonconvex optimization programs. In this work, we propose a QAOA parameter transfer scheme using Graph Attention Networks (GAT) to solve Maximum Independent Set (MIS) problems. We prepare optimized parameters for graphs of 12 and 14 vertices and use GATs to transfer their parameters to larger graphs. Additionally, we design a hybrid distributed resource-aware algorithm for MIS (HyDRA-MIS), which decomposes large problems into smaller ones that can fit onto noisy intermediate-scale quantum (NISQ) computers. We integrate our GAT-based parameter transfer approach to HyDRA-MIS and demonstrate competitive results compared to KaMIS, a state-of-the-art classical MIS solver, on graphs with several thousands vertices.Reproducibility: Our source code and data are available at https://github.com/jxsoortha/QAOA-Parameter-Transfer-via-GAT.The quantum approximate optimization algorithm (QAOA) is one of the promising variational approaches of quantum computing to solve combinatorial optimization problems. In QAOA, variational parameters need to be optimized by solving a series of nonlinear, nonconvex optimization programs. In this work, we propose a QAOA parameter transfer scheme using Graph Attention Networks (GAT) to solve Maximum Independent Set (MIS) problems. We prepare optimized parameters for graphs of 12 and 14 vertices and use GATs to transfer their parameters to larger graphs. Additionally, we design a hybrid distributed resource-aware algorithm for MIS (HyDRA-MIS), which decomposes large problems into smaller ones that can fit onto noisy intermediate-scale quantum (NISQ) computers. We integrate our GAT-based parameter transfer approach to HyDRA-MIS and demonstrate competitive results compared to KaMIS, a state-of-the-art classical MIS solver, on graphs with several thousands vertices.Reproducibility: Our source code and data are available at https://github.com/jxsoortha/QAOA-Parameter-Transfer-via-GAT.

arXiv:2504.21135IEEE High Performance Extreme Computing ConferenceSep 15, 20250 citations

β

and

γ

parameters for p layers. We compare how well the parameters found for one problem adapt to the others. Among the different problems, BPP is the one that produces the best transferable parameters, maintaining the probability of finding the optimal solution above a quadratic speedup over random guessing for problem sizes up to 42 qubits and p = 10 layers. Using the BPP parameters, we perform experiments on IonQ Harmony and Aria, Rigetti Aspen-M-3, and IBM Brisbane of MIS instances for up to 18 qubits. The results indicate that IonQ Aria yields the best overlap with the ideal probability distribution. Additionally, we show that cross-platform TL is possible using the D-Wave Advantage quantum annealer with the parameters found for BPP. We show an improvement in performance compared to the default protocols for MIS with up to 170 qubits. Our results suggest that there are QAOA parameters that generalize well for different COPs and annealing protocols.

The Quantum Approximate Optimization Algorithm (QAOA) is a leading approach for combinatorial optimization on near-term quantum devices, yet its scalability is limited by the difficulty of optimizing

2p

variational parameters for a large number

p

of layers. Recent empirical studies indicate that optimal QAOA angles exhibit concentration and transferability across problem sizes. Leveraging this observation, we propose a schedule-learning framework that transfers spectral-gap-informed adiabatic control strategies from small-scale instances to larger systems. Our method extracts the spectral gap profile of small problems and constructs a continuous schedule governed by

\partial_t s = κg^q(s)

, where

g(s)

is the instantaneous gap and

(κ, q)

are global hyperparameters. Discretizing this schedule yields closed-form expressions for all QAOA angles, reducing the classical optimization task from

2p

parameters to only

2

, independent of circuit depth. This drastic parameter compression mitigates classical optimization overhead and reduces sensitivity to barren plateau phenomena. Numerical simulations on random QUBO and 3-regular MaxCut instances demonstrate that the learnt schedules transfer effectively to larger systems while achieving competitive approximation ratios. Our results suggest that gap-informed schedule transfers provide a scalable and parameter-efficient strategy for QAOA.