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:2610.10351

Measurement-Efficient Differentiable Quantum Architecture Search for Combinatorial Optimization

Lukas Theißinger, Thore Gerlach, Christian Bauckhage

quant-phcs.LGSubmitted Oct 7, 2026• Announced Oct 8, 2026• 0 citations
arXivHTMLPDF

Abstract

Differentiable quantum architecture search (DQAS) is a promising framework for the automated design of quantum circuits, particularly for variational quantum optimization algorithms. However, its practical deployment on quantum hardware is limited by the large number of circuit measurements required during optimization, making hardware execution costly. In this work, we show that for a broad class of combinatorial optimization problems and commonly used rotational gate parameterizations, the measurement cost of DQAS can be significantly reduced without changing the optimization objective. We derive the proposed measurement reduction scheme theoretically and validate it experimentally on 3-SAT and MaxCut benchmark problems. Our approach reduces the requested gradient measurement cost by about 39 to 41% while introducing only negligible classical post-processing overhead, lowering the practical cost of executing DQAS on quantum hardware.

AI Summary

Differentiable quantum architecture search (DQAS) jointly optimizes circuit structure and gate parameters, but parameter-shift gradients require many circuit evaluations. This paper asks when those evaluations can be reduced for computational-basis-diagonal combinatorial optimization Hamiltonians without changing the objective or architecture-update rule. For Pauli-string rotations, it derives commutation-based certificates for exactly zero gradients and a one-shift gradient identity involving only Hamiltonian terms that anticommute with the gate generator. When the circuit suffix commutes with the Hamiltonian, this restricted observable remains computational-basis measurable. A Clifford suffix also permits a one-shift estimator through classical Pauli propagation and selection of contributing terms. ME-DQAS checks these conditions for each parameter and otherwise uses ordinary two-shift parameter estimation. Validation uses paired, shot-budgeted simulations on 100 3-SAT and 100 MaxCut instances, with eight qubits, eight circuit positions, and gate pool $\{R_x,R_y,R_z,\mathrm{CZ}\}$. Under a global budget of 750,000 shots, requested gradient-shot costs fall to 58.6% and 60.6% of baseline, respectively. Completed updates increase from 8.99 to 14.05 for 3-SAT and from 8.56 to 13.54 for MaxCut, with lower final normalized best-so-far loss. Zero-gradient elimination accounts for approximately 31–33 percentage points of savings; the diagonal one-shift rule contributes about eight, while the Clifford branch is negligible. Savings depend on the Hamiltonian, gate pool, and suffix structure; non-Clifford mixing can prevent eligibility. The demonstrations are small-system simulations rather than hardware tests, and the reported cost reduction concerns requested parameter-gradient shots.

Little sign of AI-generated textIncrementalUnclear noveltyMissing comparison

Error found: The abstract omits the circuit-structure conditions governing measurement savings, while its reported 39–41% reductions are established only in simulations of 8-qubit, length-8 circuits using the gate pool {Rx, Ry, Rz, CZ}, not across general DQAS architectures.

Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.

Comments
6 pages, 2 figures. Accepted at the 2026 IEEE 2nd International Conference on Quantum Artificial Intelligence (QAI). Code and data: https://github.com/Newida/ME-DQAS

Related papers

Differentiable quantum architecture search

Shi‐Xin Zhang, Chang‐Yu Hsieh, Shengyu Zhang +1 more

Abstract Quantum architecture search (QAS) is the process of automating architecture engineering of quantum circuits. It has been desired to construct a powerful and general QAS platform which can significantly accelerate current efforts to identify quantum advantages of error-prone and depth-limited quantum circuits in the NISQ era. Hereby, we propose a general framework of differentiable quantum architecture search (DQAS), which enables automated designs of quantum circuits in an end-to-end differentiable fashion. We present several examples of circuit design problems to demonstrate the power of DQAS. For instance, unitary operations are decomposed into quantum gates, noisy circuits are re-designed to improve accuracy, and circuit layouts for quantum approximation optimization algorithm are automatically discovered and upgraded for combinatorial optimization problems. These results not only manifest the vast potential of DQAS being an essential tool for the NISQ application developments, but also present an interesting research topic from the theoretical perspective as it draws inspirations from the newly emerging interdisciplinary paradigms of differentiable programming, probabilistic programming, and quantum programming.

arXiv:2010.08561•Quantum Science and Technology•Aug 8, 2022•211 citations

Quantum-Based Self-Attention Mechanism for Hardware-Aware Differentiable Quantum Architecture Search

Yuxiang Liu, Sixuan Li, Fanxu Meng +2 more

The automated design of parameterized quantum circuits for variational algorithms in the NISQ era faces a fundamental limitation, as conventional differentiable architecture search relies on classical models that fail to adequately represent quantum gate interactions under hardware noise. We introduce the Quantum-Based Self-Attention for Differentiable Quantum Architecture Search (QBSA-DQAS), a meta-learning framework featuring quantum-based self-attention and hardware-aware multi-objective search. The framework employs a two-stage quantum self-attention module that computes contextual dependencies by mapping architectural parameters through parameterized quantum circuits, replacing classical similarity metrics with quantum-derived attention scores, then applies position-wise quantum transformations for feature enrichment. Architecture search is guided by a task-agnostic multi-objective function jointly optimizing noisy expressibility and Probability of Successful Trials (PST). A post-search optimization stage applies gate commutation, fusion, and elimination to reduce circuit complexity. Experimental validation demonstrates superior performance on VQE tasks and large-scale Wireless Sensor Networks. For VQE on H$_2$, QBSA-DQAS achieves 0.9 accuracy compared to 0.89 for standard DQAS. Post-search optimization reduces discovered circuit complexity by up to 44% in gate count and 47% in depth without accuracy degradation. The framework maintains robust performance across three molecules and five IBM quantum hardware noise models. For WSN routing, discovered circuits achieve 8.6% energy reduction versus QAOA and 40.7% versus classical greedy methods, establishing the effectiveness of quantum-native architecture search for NISQ applications.

quant-pharXiv:2512.02476•Physical Review Applied•Dec 3, 2025•3 citations

Differentiable Quantum Architecture Search for Quantum Reinforcement Learning

Yize Sun, Yunpu Ma, Volker Tresp C

Differentiable quantum architecture search (DQAS) is a gradient-based framework to design quantum circuits automatically in the NISQ era. It was motivated by such as low fidelity of quantum hardware, low flexibility of circuit architecture, high circuit design cost, barren plateau (BP) problem, and periodicity of weights. People used it to address error mitigation, unitary decomposition, and quantum approximation optimization problems based on fixed datasets. Quantum reinforcement learning (QRL) is a part of quantum machine learning and often has various data. QRL usually uses a manually designed circuit. However, the pre-defined circuit needs more flexibility for different tasks, and the circuit design based on various datasets could become intractable in the case of a large circuit. The problem of whether DQAS can be applied to quantum deep Q-learning with various datasets is still open. The main target of this work is to discover the capability of DQAS to solve quantum deep Q-learning problems. We apply a gradient-based framework DQAS on reinforcement learning tasks and evaluate it in two different environments - cart pole and frozen lake. It contains input- and output weights, progressive search, and other new features. The experiments conclude that DQAS can design quantum circuits automatically and efficiently. The evaluation results show significant outperformance compared to the manually designed circuit. Furthermore, the performance of the automatically created circuit depends on whether the super-circuit learned well during the training process. This work is the first to show that gradient-based quantum architecture search is applicable to QRL tasks.

arXiv:2309.10392•IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 17, 2023•26 citations

Differentiable Architecture Search for Adversarially Robust Quantum Computer Vision

Mohamed Afane, Quanjiang Long, Haoting Shen +4 more

Current quantum neural networks suffer from extreme sensitivity to both adversarial perturbations and hardware noise, creating a significant barrier to real-world deployment. Existing robustness techniques typically sacrifice clean accuracy or require prohibitive computational resources. We propose a hybrid quantum-classical Differentiable Quantum Architecture Search (DQAS) framework that addresses these limitations by jointly optimizing circuit structure and robustness through gradient-based methods. Our approach enhances traditional DQAS with a lightweight Classical Noise Layer applied before quantum processing, enabling simultaneous optimization of gate selection and noise parameters. This design preserves the quantum circuit's integrity while introducing trainable perturbations that enhance robustness without compromising standard performance. Experimental validation on MNIST, FashionMNIST, and CIFAR datasets shows consistent improvements in both clean and adversarial accuracy compared to existing quantum architecture search methods. Under various attack scenarios, including Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), Basic Iterative Method (BIM), and Momentum Iterative Method (MIM), and under realistic quantum noise conditions, our hybrid framework maintains superior performance. Testing on actual quantum hardware confirms the practical viability of discovered architectures. These results demonstrate that strategic classical preprocessing combined with differentiable quantum architecture optimization can significantly enhance quantum neural network robustness while maintaining computational efficiency.

quant-pharXiv:2601.18058•Quantum Machine Intelligence•Jan 27, 2026•4 citations

SA-DQAS: Self-attention Enhanced Differentiable Quantum Architecture Search

Yize Sun, Jiarui Liu, Zixin Wu +2 more

We introduce SA-DQAS, a novel framework that enhances Differentiable Quantum Architecture Search (DQAS) by integrating a self-attention mechanism, enabling more effective quantum circuit design for variational quantum algorithms. Unlike DQAS, which treats placeholders independently, SA-DQAS captures inter-placeholder dependencies to improve architecture learning. We evaluate SA-DQAS across multiple tasks, including MaxCut, Job-Shop Scheduling Problem (JSSP), quantum chemistry simulation, and error mitigation. Experimental results show that SA-DQAS outperforms baselines and prior QAS methods in most cases, producing architectures with better stability, convergence, and noise resilience. To assess scalability and hardware readiness, we further test SA-DQAS-generated circuits on IBM's quantum device using the MaxCut problem. Circuits trained on small graphs are stacked to solve larger instances without retraining, demonstrating generalization to real hardware and larger problem sizes. Our results suggest that SA-DQAS not only improves circuit quality during training but also enables practical deployment on near-term quantum devices. This research represents the first successful integration of self-attention mechanism with DQAS.

arXiv:2406.08882•Jun 13, 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
Differentiable quantum architecture search (DQAS) is a promising framework for the automated design of quantum circuits, particularly for variational quantum optimization algorithms. However, its practical deployment on quantum hardware is limited by the large number of circuit measurements required during optimization, making hardware execution costly. In this work, we show that for a broad class of combinatorial optimization problems and commonly used rotational gate parameterizations, the measurement cost of DQAS can be significantly reduced without changing the optimization objective. We derive the proposed measurement reduction scheme theoretically and validate it experimentally on 3-SAT and MaxCut benchmark problems. Our approach reduces the requested gradient measurement cost by about 39 to 41% while introducing only negligible classical post-processing overhead, lowering the practical cost of executing DQAS on quantum hardware.
Differentiable quantum architecture search (DQAS) jointly optimizes circuit structure and gate parameters, but parameter-shift gradients require many circuit evaluations. This paper asks when those evaluations can be reduced for computational-basis-diagonal combinatorial optimization Hamiltonians without changing the objective or architecture-update rule.
For Pauli-string rotations, it derives commutation-based certificates for exactly zero gradients and a one-shift gradient identity involving only Hamiltonian terms that anticommute with the gate generator. When the circuit suffix commutes with the Hamiltonian, this restricted observable remains computational-basis measurable. A Clifford suffix also permits a one-shift estimator through classical Pauli propagation and selection of contributing terms. ME-DQAS checks these conditions for each parameter and otherwise uses ordinary two-shift parameter estimation.
Validation uses paired, shot-budgeted simulations on 100 3-SAT and 100 MaxCut instances, with eight qubits, eight circuit positions, and gate pool {Rx,Ry,Rz,CZ}\{R_x,R_y,R_z,\mathrm{CZ}\}{Rx​,Ry​,Rz​,CZ}. Under a global budget of 750,000 shots, requested gradient-shot costs fall to 58.6% and 60.6% of baseline, respectively. Completed updates increase from 8.99 to 14.05 for 3-SAT and from 8.56 to 13.54 for MaxCut, with lower final normalized best-so-far loss. Zero-gradient elimination accounts for approximately 31–33 percentage points of savings; the diagonal one-shift rule contributes about eight, while the Clifford branch is negligible.
Savings depend on the Hamiltonian, gate pool, and suffix structure; non-Clifford mixing can prevent eligibility. The demonstrations are small-system simulations rather than hardware tests, and the reported cost reduction concerns requested parameter-gradient shots.
Abstract Quantum architecture search (QAS) is the process of automating architecture engineering of quantum circuits. It has been desired to construct a powerful and general QAS platform which can significantly accelerate current efforts to identify quantum advantages of error-prone and depth-limited quantum circuits in the NISQ era. Hereby, we propose a general framework of differentiable quantum architecture search (DQAS), which enables automated designs of quantum circuits in an end-to-end differentiable fashion. We present several examples of circuit design problems to demonstrate the power of DQAS. For instance, unitary operations are decomposed into quantum gates, noisy circuits are re-designed to improve accuracy, and circuit layouts for quantum approximation optimization algorithm are automatically discovered and upgraded for combinatorial optimization problems. These results not only manifest the vast potential of DQAS being an essential tool for the NISQ application developments, but also present an interesting research topic from the theoretical perspective as it draws inspirations from the newly emerging interdisciplinary paradigms of differentiable programming, probabilistic programming, and quantum programming.
The automated design of parameterized quantum circuits for variational algorithms in the NISQ era faces a fundamental limitation, as conventional differentiable architecture search relies on classical models that fail to adequately represent quantum gate interactions under hardware noise. We introduce the Quantum-Based Self-Attention for Differentiable Quantum Architecture Search (QBSA-DQAS), a meta-learning framework featuring quantum-based self-attention and hardware-aware multi-objective search. The framework employs a two-stage quantum self-attention module that computes contextual dependencies by mapping architectural parameters through parameterized quantum circuits, replacing classical similarity metrics with quantum-derived attention scores, then applies position-wise quantum transformations for feature enrichment. Architecture search is guided by a task-agnostic multi-objective function jointly optimizing noisy expressibility and Probability of Successful Trials (PST). A post-search optimization stage applies gate commutation, fusion, and elimination to reduce circuit complexity. Experimental validation demonstrates superior performance on VQE tasks and large-scale Wireless Sensor Networks. For VQE on H2_22​, QBSA-DQAS achieves 0.9 accuracy compared to 0.89 for standard DQAS. Post-search optimization reduces discovered circuit complexity by up to 44% in gate count and 47% in depth without accuracy degradation. The framework maintains robust performance across three molecules and five IBM quantum hardware noise models. For WSN routing, discovered circuits achieve 8.6% energy reduction versus QAOA and 40.7% versus classical greedy methods, establishing the effectiveness of quantum-native architecture search for NISQ applications.
Differentiable quantum architecture search (DQAS) is a gradient-based framework to design quantum circuits automatically in the NISQ era. It was motivated by such as low fidelity of quantum hardware, low flexibility of circuit architecture, high circuit design cost, barren plateau (BP) problem, and periodicity of weights. People used it to address error mitigation, unitary decomposition, and quantum approximation optimization problems based on fixed datasets. Quantum reinforcement learning (QRL) is a part of quantum machine learning and often has various data. QRL usually uses a manually designed circuit. However, the pre-defined circuit needs more flexibility for different tasks, and the circuit design based on various datasets could become intractable in the case of a large circuit. The problem of whether DQAS can be applied to quantum deep Q-learning with various datasets is still open. The main target of this work is to discover the capability of DQAS to solve quantum deep Q-learning problems. We apply a gradient-based framework DQAS on reinforcement learning tasks and evaluate it in two different environments - cart pole and frozen lake. It contains input- and output weights, progressive search, and other new features. The experiments conclude that DQAS can design quantum circuits automatically and efficiently. The evaluation results show significant outperformance compared to the manually designed circuit. Furthermore, the performance of the automatically created circuit depends on whether the super-circuit learned well during the training process. This work is the first to show that gradient-based quantum architecture search is applicable to QRL tasks.
Current quantum neural networks suffer from extreme sensitivity to both adversarial perturbations and hardware noise, creating a significant barrier to real-world deployment. Existing robustness techniques typically sacrifice clean accuracy or require prohibitive computational resources. We propose a hybrid quantum-classical Differentiable Quantum Architecture Search (DQAS) framework that addresses these limitations by jointly optimizing circuit structure and robustness through gradient-based methods. Our approach enhances traditional DQAS with a lightweight Classical Noise Layer applied before quantum processing, enabling simultaneous optimization of gate selection and noise parameters. This design preserves the quantum circuit's integrity while introducing trainable perturbations that enhance robustness without compromising standard performance. Experimental validation on MNIST, FashionMNIST, and CIFAR datasets shows consistent improvements in both clean and adversarial accuracy compared to existing quantum architecture search methods. Under various attack scenarios, including Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), Basic Iterative Method (BIM), and Momentum Iterative Method (MIM), and under realistic quantum noise conditions, our hybrid framework maintains superior performance. Testing on actual quantum hardware confirms the practical viability of discovered architectures. These results demonstrate that strategic classical preprocessing combined with differentiable quantum architecture optimization can significantly enhance quantum neural network robustness while maintaining computational efficiency.
We introduce SA-DQAS, a novel framework that enhances Differentiable Quantum Architecture Search (DQAS) by integrating a self-attention mechanism, enabling more effective quantum circuit design for variational quantum algorithms. Unlike DQAS, which treats placeholders independently, SA-DQAS captures inter-placeholder dependencies to improve architecture learning. We evaluate SA-DQAS across multiple tasks, including MaxCut, Job-Shop Scheduling Problem (JSSP), quantum chemistry simulation, and error mitigation. Experimental results show that SA-DQAS outperforms baselines and prior QAS methods in most cases, producing architectures with better stability, convergence, and noise resilience. To assess scalability and hardware readiness, we further test SA-DQAS-generated circuits on IBM's quantum device using the MaxCut problem. Circuits trained on small graphs are stacked to solve larger instances without retraining, demonstrating generalization to real hardware and larger problem sizes. Our results suggest that SA-DQAS not only improves circuit quality during training but also enables practical deployment on near-term quantum devices. This research represents the first successful integration of self-attention mechanism with DQAS.
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.