Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2512.22434

Quantum-Circuit Framework for Two-Stage Stochastic Programming via QAOA Integrated with a Quantum Generative Neural Network

Taihei Kuroiwa, Daiki Yamazaki, Keita Takahashi, Kodai Shiba, Chih-Chieh Chen, Tomah Sogabe

quant-phSubmitted Dec 27, 2025• Announced Dec 30, 2025• 1 citation
arXivHTMLPDF

Abstract

Two-stage stochastic programming often discretizes uncertainty into scenarios, but scenario enumeration makes expected recourse evaluation scale at least linearly in the scenario count. We propose qGAN-QAOA, a unified quantum-circuit workflow in which a pre-trained quantum generative adversarial network encodes the scenario distribution and QAOA optimizes first-stage decisions by minimizing the full two-stage objective, including expected recourse cost. With the qGAN parameters fixed after training, we evaluate the objective as the expectation value of a problem Hamiltonian and optimize only the QAOA variational parameters. We interpret non-anticipativity as a condition on measurement outcome statistics and prove that the first-stage measurement marginal is independent of the scenario. For uniformly discretized uncertainty, the diagonal operator encoding the uncertainty admits a sparse Pauli-Z expansion via the Walsh--Hadamard transform, yielding polylogarithmic scaling of gate count and circuit depth with the number of scenarios. Numerical experiments on the stochastic unit commitment problem (UCP) with photovoltaic (PV) uncertainty compare the expected cost of the proposed method with classical expected-value and two-stage stochastic programming baselines, demonstrating the effectiveness of qGAN-QAOA as a two-stage decision model.

Comments
50 pages, 7 figures, 3 tables

Related papers

Quantum approximate stochastic combinatorial optimisation

Edric Matwiejew, Paulo E. Santos, Jingbo B. Wang +1 more

Two-stage stochastic combinatorial optimisation concerns discrete decisions made before all relevant information is known. An initial decision is made; once uncertainty is resolved, it can be adapted to the realised scenario, at a cost. The aim is to find the initial decision that minimises the upfront cost plus the expected cost of optimal adaptation. The first-stage decision problem is often NP-hard, and computing the expected minimum recourse cost can be $\#\mathrm{P}$-hard for a single first-stage candidate. We introduce Quantum Approximate Stochastic Combinatorial Optimisation (QASCO), a variational quantum-walk ansatz that coherently incorporates scenario-dependent recourse into its dynamics to search over first-stage decisions without explicitly evaluating expected minimum recourse costs. We demonstrate QASCO for MaxCut with stochastic edge weights, obtain a circuit with polynomial per-layer gate complexity, and study the ansatz via exact state-vector simulation. Across the instances considered, QASCO concentrates amplitude more effectively on stochastic-optimal first-stage decisions than a previously proposed two-stage QAOA construction. We further show that the ansatz can be calibrated using a depth-independent number of parameters and applied to unseen instances without further circuit-parameter optimisation, including joint decision--scenario--recourse spaces spanning more than $2^{32}$ configurations. Under a query-cost model, comparison with the tested classical heuristics using sample-average approximations of the expected minimum recourse cost shows that QASCO more reliably reaches globally optimal first-stage solutions while requiring fewer cut evaluations. These results show how to incorporate scenario-dependent recourse into the ansatz dynamics, providing a general framework for variational quantum walks in two-stage stochastic combinatorial optimisation.

quant-pharXiv:2610.22876•Oct 19, 2026•0 citations

A Quantum-Circuit Analogue for Probabilistic Decision Commitment

Ondřej Šrámek

We present a minimal, fully reproducible quantum-circuit analogue for probabilistic decisioncommitment. A two-qubit variational quantum circuit, run on a classical statevector simulator,angle-encodes binary inputs and is trained (COBYLA) against a Pauli-Z expectation objective.Two experiments are reported: (1) an untrained circuit yields a probabilistic measurementspread that training reshapes toward a near-deterministic outcome — the collapse itself beingperformed by measurement — modelling an unresolved decision distribution resolving into acommitment; and (2) the same architecture learns XOR (4/4, zero training loss), the canonicalnon-linearly-separable function, with the entangling operation supplying the cross-featureinteraction required in this ansatz. We read the Pauli-Z expectation as a graded confidencesignal and propose a magnitude threshold as a measurable commit condition for probabilisticdecision systems, including external-scaffolding continuity frameworks for stateless languagemodels. We claim no quantum advantage and no quantum execution of language models; thecontribution is pedagogical clarity and a decision-commitment design lens — established resultsin quantum machine learning, reframed for decision discipline. All code is provided.

•Jul 8, 2026•0 citations

Extending QAOA-GPT to Higher-Order Quantum Optimization Problems

Leanto Sunny, Abhinav Rijal, George Siopsis

The recently proposed QAOA-GPT framework demonstrated that generative pre-trained transformers can learn mappings between problem graphs and optimized quantum circuits for the Quantum Approximate Optimization Algorithm (QAOA). In this work, we extend QAOA-GPT to Higher-Order Unconstrained Binary Optimization (HUBO) problems, focusing on spin-glass Hamiltonians that include cubic interaction terms. Using FEATHER graph embeddings to encode topological information, we train the model on graph-circuit pairs generated via ADAPT-QAOA and evaluate its performance on 8- and 16-qubit instances embedded on heavy-hex lattices. The generative model produces adaptive QAOA-like circuits and corresponding variational parameters in a single forward pass, bypassing the iterative classical optimization loop. The generated circuits achieve average approximation ratios exceeding 0.95, closely matching classically optimized ADAPT-QAOA results, while maintaining consistent parameter distributions across circuit depths. These results demonstrate that QAOA-GPT generalizes effectively to higher-order cost Hamiltonians and complex energy landscapes, establishing generative modeling as a scalable pathway toward autonomous variational circuit design and quantum algorithm discovery in the NISQ era.

quant-pharXiv:2511.07391•Nov 11, 2025•4 citations

Hybrid GRU-CNN bilinear parameters initialization for quantum approximate optimization algorithm

Zuyu Xu, Pengnian Cai, Kang Shen +7 more

Abstract The Quantum Approximate Optimization Algorithm (QAOA), a pivotal paradigm in the realm of variational quantum algorithms (VQAs), offers promising computational advantages for tackling combinatorial optimization problems. Well-defined initial circuit parameters, responsible for preparing a parameterized quantum state encoding the solution, play a key role in optimizing QAOA. However, classical optimization techniques encounter challenges in discerning optimal parameters that align with the optimal solution. In this work, we propose a hybrid optimization approach that integrates Gated Recurrent Units (GRU), Convolutional Neural Networks (CNN), and a bilinear strategy as an innovative alternative to conventional optimizers for predicting optimal parameters of QAOA circuits. GRU serves to stochastically initialize favorable parameters for depth-1 circuits, while CNN predicts initial parameters for depth-2 circuits based on the optimized parameters of depth-1 circuits. To assess the efficacy of our approach, we conducted a comparative analysis with traditional initialization methods using QAOA on Erdős-Rényi graph instances, revealing superior optimal approximation ratios. We employ the bilinear strategy to initialize QAOA circuit parameters at greater depths, with reference parameters obtained from GRU-CNN optimization. This approach allows us to forecast parameters for a depth-12 QAOA circuit, yielding a remarkable approximation ratio of 0.998 across 10 qubits, which surpasses that of the random initialization strategy and the PPN2 method at a depth of 10. The proposed hybrid GRU-CNN bilinear optimization method significantly improves the effectiveness and accuracy of parameters initialization, offering a promising iterative framework for QAOA that elevates its performance.

arXiv:2311.07869•Physica Scripta•Jun 20, 2024•3 citations

Benchmarking Modular Optimization Strategies for Parameterized Quantum Circuits

Carla Cotea, Stefan Balauca, Andreea Arusoaie

Training parameterized quantum circuits requires balancing optimization progress with limited evaluation budgets and the statistical uncertainty of near-term quantum hardware. We present a modular benchmarking framework that separates quantum search-direction estimation from classical parameter-update rules, allowing their interactions and sensitivities to be examined independently. We evaluate a suite of gradient-based, stochastic, and derivative-free optimizers across combinatorial optimization using the Quantum Approximate Optimization Algorithm (QAOA), supervised quantum machine learning using Iris classification and a quantum convolutional neural network (QCNN) for binary MNIST classification, and quantum chemistry using the variational quantum eigensolver (VQE) for molecular hydrogen. By separating objective evaluations from sample-circuit costs under finite-shot simulation and physical execution on a 156-qubit processor, we compare optimizer behavior across workloads with different parameter counts and measurement requirements. Four selected simulator and hardware case studies report terminal and best observed objectives separately, alongside post-training classifier accuracies. The comparisons include selected MaxCut and hydrogen trajectories and illustrate workload-dependent objective changes and evaluation costs, while the simulator benchmark compares both peak and mean performance across three seeds. The hardware runs do not establish an optimizer ranking or isolate a causal effect of device noise.

quant-pharXiv:2610.10254•Oct 8, 2026•0 citations

A Hybrid Quantum-Classical Generative Adversarial Network for Near-Term Quantum Processors

Albha O’Dwyer Boyle, Gholamreza Nikandish

In this article, we present a hybrid quantum-classical generative adversarial network (GAN) for near-term quantum processors. The hybrid GAN comprises a variational generator and a discriminator quantum neural network, which are trained using a classic computer. The generator network is realized using angle-encoding and variational quantum circuits. The discriminator network is realized using multi-stage trainable encoding quantum circuits. A modular design approach is proposed for quantum neural networks which allows control on their depth to compromise accuracy and circuit complexity. Moreover, this modular approach makes the quantum neural networks amenable to scaling up the dimension of dataset and the number of qubits. Gradients of the loss functions are derived using the same quantum circuits used for the implementation of quantum neural networks to prevent the need for extra quantum circuits or auxiliary qubits. The quantum simulations are performed using the IBM Qiskit open-source software development kit (SDK), while the training of the hybrid quantum-classical GAN is conducted using the mini-batch stochastic gradient descent (SGD) optimization on a classic computer. The hybrid quantum-classical GAN is realized using a two-qubit system with different discriminator network structures. The best performance is achieved using a five-stage discriminator network comprising 63 quantum gates and 31 trainable parameters, with the Kullback-Leibler (KL) and Jensen-Shannon (JS) divergence scores of 0.39 and 0.52, respectively, for the similarity between the real and generated data distributions.

arXiv:2307.03269•IEEE Access•Jan 1, 2024•19 citations
Two-stage stochastic programming often discretizes uncertainty into scenarios, but scenario enumeration makes expected recourse evaluation scale at least linearly in the scenario count. We propose qGAN-QAOA, a unified quantum-circuit workflow in which a pre-trained quantum generative adversarial network encodes the scenario distribution and QAOA optimizes first-stage decisions by minimizing the full two-stage objective, including expected recourse cost. With the qGAN parameters fixed after training, we evaluate the objective as the expectation value of a problem Hamiltonian and optimize only the QAOA variational parameters. We interpret non-anticipativity as a condition on measurement outcome statistics and prove that the first-stage measurement marginal is independent of the scenario. For uniformly discretized uncertainty, the diagonal operator encoding the uncertainty admits a sparse Pauli-Z expansion via the Walsh--Hadamard transform, yielding polylogarithmic scaling of gate count and circuit depth with the number of scenarios. Numerical experiments on the stochastic unit commitment problem (UCP) with photovoltaic (PV) uncertainty compare the expected cost of the proposed method with classical expected-value and two-stage stochastic programming baselines, demonstrating the effectiveness of qGAN-QAOA as a two-stage decision model.
Two-stage stochastic combinatorial optimisation concerns discrete decisions made before all relevant information is known. An initial decision is made; once uncertainty is resolved, it can be adapted to the realised scenario, at a cost. The aim is to find the initial decision that minimises the upfront cost plus the expected cost of optimal adaptation. The first-stage decision problem is often NP-hard, and computing the expected minimum recourse cost can be #P\#\mathrm{P}#P-hard for a single first-stage candidate. We introduce Quantum Approximate Stochastic Combinatorial Optimisation (QASCO), a variational quantum-walk ansatz that coherently incorporates scenario-dependent recourse into its dynamics to search over first-stage decisions without explicitly evaluating expected minimum recourse costs. We demonstrate QASCO for MaxCut with stochastic edge weights, obtain a circuit with polynomial per-layer gate complexity, and study the ansatz via exact state-vector simulation. Across the instances considered, QASCO concentrates amplitude more effectively on stochastic-optimal first-stage decisions than a previously proposed two-stage QAOA construction. We further show that the ansatz can be calibrated using a depth-independent number of parameters and applied to unseen instances without further circuit-parameter optimisation, including joint decision--scenario--recourse spaces spanning more than 2322^{32}232 configurations. Under a query-cost model, comparison with the tested classical heuristics using sample-average approximations of the expected minimum recourse cost shows that QASCO more reliably reaches globally optimal first-stage solutions while requiring fewer cut evaluations. These results show how to incorporate scenario-dependent recourse into the ansatz dynamics, providing a general framework for variational quantum walks in two-stage stochastic combinatorial optimisation.
We present a minimal, fully reproducible quantum-circuit analogue for probabilistic decisioncommitment. A two-qubit variational quantum circuit, run on a classical statevector simulator,angle-encodes binary inputs and is trained (COBYLA) against a Pauli-Z expectation objective.Two experiments are reported: (1) an untrained circuit yields a probabilistic measurementspread that training reshapes toward a near-deterministic outcome — the collapse itself beingperformed by measurement — modelling an unresolved decision distribution resolving into acommitment; and (2) the same architecture learns XOR (4/4, zero training loss), the canonicalnon-linearly-separable function, with the entangling operation supplying the cross-featureinteraction required in this ansatz. We read the Pauli-Z expectation as a graded confidencesignal and propose a magnitude threshold as a measurable commit condition for probabilisticdecision systems, including external-scaffolding continuity frameworks for stateless languagemodels. We claim no quantum advantage and no quantum execution of language models; thecontribution is pedagogical clarity and a decision-commitment design lens — established resultsin quantum machine learning, reframed for decision discipline. All code is provided.
The recently proposed QAOA-GPT framework demonstrated that generative pre-trained transformers can learn mappings between problem graphs and optimized quantum circuits for the Quantum Approximate Optimization Algorithm (QAOA). In this work, we extend QAOA-GPT to Higher-Order Unconstrained Binary Optimization (HUBO) problems, focusing on spin-glass Hamiltonians that include cubic interaction terms. Using FEATHER graph embeddings to encode topological information, we train the model on graph-circuit pairs generated via ADAPT-QAOA and evaluate its performance on 8- and 16-qubit instances embedded on heavy-hex lattices. The generative model produces adaptive QAOA-like circuits and corresponding variational parameters in a single forward pass, bypassing the iterative classical optimization loop. The generated circuits achieve average approximation ratios exceeding 0.95, closely matching classically optimized ADAPT-QAOA results, while maintaining consistent parameter distributions across circuit depths. These results demonstrate that QAOA-GPT generalizes effectively to higher-order cost Hamiltonians and complex energy landscapes, establishing generative modeling as a scalable pathway toward autonomous variational circuit design and quantum algorithm discovery in the NISQ era.
Abstract The Quantum Approximate Optimization Algorithm (QAOA), a pivotal paradigm in the realm of variational quantum algorithms (VQAs), offers promising computational advantages for tackling combinatorial optimization problems. Well-defined initial circuit parameters, responsible for preparing a parameterized quantum state encoding the solution, play a key role in optimizing QAOA. However, classical optimization techniques encounter challenges in discerning optimal parameters that align with the optimal solution. In this work, we propose a hybrid optimization approach that integrates Gated Recurrent Units (GRU), Convolutional Neural Networks (CNN), and a bilinear strategy as an innovative alternative to conventional optimizers for predicting optimal parameters of QAOA circuits. GRU serves to stochastically initialize favorable parameters for depth-1 circuits, while CNN predicts initial parameters for depth-2 circuits based on the optimized parameters of depth-1 circuits. To assess the efficacy of our approach, we conducted a comparative analysis with traditional initialization methods using QAOA on Erdős-Rényi graph instances, revealing superior optimal approximation ratios. We employ the bilinear strategy to initialize QAOA circuit parameters at greater depths, with reference parameters obtained from GRU-CNN optimization. This approach allows us to forecast parameters for a depth-12 QAOA circuit, yielding a remarkable approximation ratio of 0.998 across 10 qubits, which surpasses that of the random initialization strategy and the PPN2 method at a depth of 10. The proposed hybrid GRU-CNN bilinear optimization method significantly improves the effectiveness and accuracy of parameters initialization, offering a promising iterative framework for QAOA that elevates its performance.
Training parameterized quantum circuits requires balancing optimization progress with limited evaluation budgets and the statistical uncertainty of near-term quantum hardware. We present a modular benchmarking framework that separates quantum search-direction estimation from classical parameter-update rules, allowing their interactions and sensitivities to be examined independently. We evaluate a suite of gradient-based, stochastic, and derivative-free optimizers across combinatorial optimization using the Quantum Approximate Optimization Algorithm (QAOA), supervised quantum machine learning using Iris classification and a quantum convolutional neural network (QCNN) for binary MNIST classification, and quantum chemistry using the variational quantum eigensolver (VQE) for molecular hydrogen. By separating objective evaluations from sample-circuit costs under finite-shot simulation and physical execution on a 156-qubit processor, we compare optimizer behavior across workloads with different parameter counts and measurement requirements. Four selected simulator and hardware case studies report terminal and best observed objectives separately, alongside post-training classifier accuracies. The comparisons include selected MaxCut and hydrogen trajectories and illustrate workload-dependent objective changes and evaluation costs, while the simulator benchmark compares both peak and mean performance across three seeds. The hardware runs do not establish an optimizer ranking or isolate a causal effect of device noise.
In this article, we present a hybrid quantum-classical generative adversarial network (GAN) for near-term quantum processors. The hybrid GAN comprises a variational generator and a discriminator quantum neural network, which are trained using a classic computer. The generator network is realized using angle-encoding and variational quantum circuits. The discriminator network is realized using multi-stage trainable encoding quantum circuits. A modular design approach is proposed for quantum neural networks which allows control on their depth to compromise accuracy and circuit complexity. Moreover, this modular approach makes the quantum neural networks amenable to scaling up the dimension of dataset and the number of qubits. Gradients of the loss functions are derived using the same quantum circuits used for the implementation of quantum neural networks to prevent the need for extra quantum circuits or auxiliary qubits. The quantum simulations are performed using the IBM Qiskit open-source software development kit (SDK), while the training of the hybrid quantum-classical GAN is conducted using the mini-batch stochastic gradient descent (SGD) optimization on a classic computer. The hybrid quantum-classical GAN is realized using a two-qubit system with different discriminator network structures. The best performance is achieved using a five-stage discriminator network comprising 63 quantum gates and 31 trainable parameters, with the Kullback-Leibler (KL) and Jensen-Shannon (JS) divergence scores of 0.39 and 0.52, respectively, for the similarity between the real and generated data distributions.