Neural QAOA$^{2}$: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial Optimization

• URL: http://arxiv.org/abs/2605.13072v1
• Date: Wed, 13 May 2026 06:43:10 GMT
• Title: Neural QAOA$^{2}$: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial Optimization
• Abstract summary: We propose Neural QAOA$2$, an end-to-end differentiable framework that jointly generates graph partitions and initial parameters.<n>By integrating a generative evaluative network (GEN), our method utilizes a differentiable quantum evaluator as a high-fidelity performance surrogate.<n>Experiments on 183 QUBO, Ising, and MaxCut instances (21 to 1000 variables) demonstrate that our gradient-driven approach broadly outperforms baselines.
• Score: 3.7086487199744127
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The quantum approximate optimization algorithm (QAOA) holds promise for combinatorial optimization but is constrained by limited qubits. While divide-and-conquer frameworks like QAOA$^{2}$ address scalability by partitioning graphs into subgraphs, existing methods suffer from two fundamental limitations: i) misalignment between heuristic partitioning metrics and quantum optimization goals, and ii) topology-blind parameter initialization that leads to optimization cold starts. To bridge these gaps, we propose Neural QAOA$^{2}$, an end-to-end differentiable framework that jointly generates graph partitions and initial parameters. By integrating a generative evaluative network (GEN), our method utilizes a differentiable quantum evaluator as a high-fidelity performance surrogate to provide direct gradient guidance, enabling the joint generator to learn the intrinsic mapping from graph topology to high-quality partition and parameter configurations. Extensive experiments on 183 QUBO, Ising, and MaxCut instances (21 to 1000 variables) demonstrate that our gradient-driven approach broadly outperforms heuristic baselines, ranking first on 101 instances. It exhibits zero-shot generalization across out-of-distribution graph topologies and scales.

Related papers

• Emergent Problem-Graph Alignment in RL-Discovered Entanglement Topologies for QAOA [3.03715087930992]
  We investigate whether a reinforcement learning agent can discover more effective entanglement topologies for QAOA-based MaxCut optimization without direct access to the problem graph.<n>Our results reveal a trainability--express trade-off governed by topology density and suggest that the variational optimization landscape implicitly encodes structural information about the problem Hamiltonian.
  arXiv  Detail & Related papers  (2026-08-07T18:17:08Z)
• Scalable Quantum Walk-Based Heuristics for the Minimum Vertex Cover Problem [0.0]
  We propose a novel quantum algorithm for the Minimum Vertex Cover (MVC) problem based on continuous-time quantum walks (CTQWs)<n>In this framework, the coherent propagation of a quantum walker over a graph encodes its structural properties into state amplitudes.<n>We show that the CTQW-based algorithm consistently achieves superior approximation ratios and exhibits remarkable robustness with respect to network topology.
  arXiv  Detail & Related papers  (2025-12-02T17:04:57Z)
• Systematic improvement of the quantum approximate optimisation ansatz for combinatorial optimisation using quantum subspace expansion [0.0]
  I study the enhancement of the quantum approximate optimisation ansatz (QAOA) with a generator coordinate method (GCM)<n>I achieve systematic performances improvements in the approximation ratio and fidelity for the maximal independent set on Erd"os-R'enyi graphs.
  arXiv  Detail & Related papers  (2025-06-23T12:54:06Z)
• A Gradient Meta-Learning Joint Optimization for Beamforming and Antenna Position in Pinching-Antenna Systems [63.213207442368294]
  We consider a novel optimization design for multi-waveguide pinching-antenna systems.<n>The proposed GML-JO algorithm is robust to different choices and better performance compared with the existing optimization methods.
  arXiv  Detail & Related papers  (2025-06-14T17:35:27Z)
• A Quantum Genetic Algorithm Framework for the MaxCut Problem [49.59986385400411]
  The proposed method introduces a Quantum Genetic Algorithm (QGA) using a Grover-based evolutionary framework and divide-and-conquer principles.<n>On complete graphs, the proposed method consistently achieves the true optimal MaxCut values, outperforming the Semidefinite Programming (SDP) approach.<n>On ErdHos-R'enyi random graphs, the QGA demonstrates competitive performance, achieving median solutions within 92-96% of the SDP results.
  arXiv  Detail & Related papers  (2025-01-02T05:06:16Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Similarity-Based Parameter Transferability in the Quantum Approximate Optimization Algorithm [2.985148456817082]
  We show clustering of optimal QAOA parameters around specific values. successful transferability of parameters between different QAOA instances can be explained. We show that one can use optimal donor graph QAOA parameters as near-optimal parameters for larger acceptor graphs with comparable approximation ratios.
  arXiv  Detail & Related papers  (2023-07-11T16:35:49Z)
• An Expressive Ansatz for Low-Depth Quantum Approximate Optimisation [0.23999111269325263]
  The quantum approximate optimisation algorithm (QAOA) is a hybrid quantum-classical algorithm used to approximately solve optimisation problems. While QAOA can be implemented on NISQ devices, physical limitations can limit circuit depth and decrease performance. This work introduces the eXpressive QAOA (XQAOA) that assigns more classical parameters to the ansatz to improve its performance at low depths.
  arXiv  Detail & Related papers  (2023-02-09T07:47:06Z)
• Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization [108.35402316802765]
  We propose a new first-order optimization algorithm -- AcceleratedGradient-OptimisticGradient (AG-OG) Ascent. We show that AG-OG achieves the optimal convergence rate (up to a constant) for a variety of settings. We extend our algorithm to extend the setting and achieve the optimal convergence rate in both bi-SC-SC and bi-C-SC settings.
  arXiv  Detail & Related papers  (2022-10-31T17:59:29Z)
• Automatic and effective discovery of quantum kernels [41.61572387137452]
  Quantum computing can empower machine learning models by enabling kernel machines to leverage quantum kernels for representing similarity measures between data.<n>We present an approach to this problem, which employs optimization techniques, similar to those used in neural architecture search and AutoML.<n>The results obtained by testing our approach on a high-energy physics problem demonstrate that, in the best-case scenario, we can either match or improve testing accuracy with respect to the manual design approach.
  arXiv  Detail & Related papers  (2022-09-22T16:42:14Z)
• Twisted hybrid algorithms for combinatorial optimization [68.8204255655161]
  Proposed hybrid algorithms encode a cost function into a problem Hamiltonian and optimize its energy by varying over a set of states with low circuit complexity. We show that for levels $p=2,ldots, 6$, the level $p$ can be reduced by one while roughly maintaining the expected approximation ratio.
  arXiv  Detail & Related papers  (2022-03-01T19:47:16Z)
• Parameters Fixing Strategy for Quantum Approximate Optimization Algorithm [0.0]
  We propose a strategy to give high approximation ratio on average, even at large circuit depths, by initializing QAOA with the optimal parameters obtained from the previous depths. We test our strategy on the Max-cut problem of certain classes of graphs such as the 3-regular graphs and the Erd"os-R'enyi graphs.
  arXiv  Detail & Related papers  (2021-08-11T15:44:16Z)
• Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework [100.36569795440889]
  This work is on the iteration of zero-th-order (ZO) optimization which does not require first-order information. We show that with a graceful design in coordinate importance sampling, the proposed ZO optimization method is efficient both in terms of complexity as well as as function query cost.
  arXiv  Detail & Related papers  (2020-12-21T17:29:58Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.