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:2603.16321

How Quantum Circuits Actually Learn: A Causal Identification of Genuine Quantum Contributions

Cyrille Yetuyetu Kesiku, Begonya Garcia-Zapirain

quant-phmath.QASubmitted Mar 17, 2026• Announced Mar 18, 2026• 3 citations
arXivHTMLPDF

Abstract

Attributing performance gains in quantum machine learning to genuine quantum resources rather than to classical architectural scaling remains an open methodological challenge. We address this by introducing a counterfactual causal mediation framework that decomposes inter-architectural performance differences into direct effects, attributable to circuit parameterization and expressivity, and indirect effects mediated by quantum information-theoretic observables: entanglement entropy, purity, linear entropy, and quantum mutual information. Applying this framework to five circuit topologies and three benchmark datasets (across 43 validated configurations) reveals that direct architectural contributions systematically exceed quantum-mediated effects, with a mean ratio of 13.1:1 and a mean indirect contribution of 0.82%. These results suggest that current variational quantum circuits operate substantially below their quantum potential, and that principled resource-aware circuit design represents a tractable path toward measurable quantum-mediated performance gains.

Related papers

Noise or Signal? A Causal Mediation Analysis of Quantum Circuit Learning Under Real Hardware Noise

Cyrille YetuYetu Kesiku, Begonya García-Zapirain

We deploy a Quantum Counterfactual Mediation Analysis (QCMA) framework on IBM Quantum processors to ask a precise, hardware-grounded question: are causal regimes identified in noiseless simulation preserved under real quantum noise? Integrating partial quantum state tomography with a linear structural equation model, we decompose inter-architectural performance contrasts into direct effects and indirect quantum-mediated effects across twelve experiments spanning three circuit topologies and two benchmark datasets. Five of six topology-dataset pairs (83%) retain their causal regime when migrating from noiseless simulation to physical hardware. Decoherence inflates quantum-mediated contributions by up to one order of magnitude a noise artefact, not quantum advantage while the Neutral regime dominates both backend. These findings indicate that hardware noise may substantially limit the effective utilization of quantum resources in current NISQ circuits, and motivate further investigation into coherence-preserving circuit design strategies.

IEEE International Conference on Quantum Software (QSW)•Jul 1, 2026•0 citations

Regression of Functions by Quantum Neural Networks Circuits

Fernando M. de Paula Neto, Lucas dos Reis Silva, Paulo S. G. de Mattos Neto +1 more

The performance of quantum neural network models depends strongly on architectural decisions, including circuit depth, placement of parametrized operations, and data-encoding strategies. Selecting an effective architecture is challenging and closely related to the classical difficulty of choosing suitable neural-network topologies, which is computationally hard. This work investigates automated quantum-circuit construction for regression tasks and introduces a genetic-algorithm framework that discovers Reduced Regressor QNN architectures. The approach explores depth, parametrized gate configurations, and flexible data re-uploading patterns, formulating the construction of quantum regressors as an optimization process. The discovered circuits are evaluated against seventeen classical regression models on twenty-two nonlinear benchmark functions and four analytical functions. Although classical methods often achieve comparable results, they typically require far more parameters, whereas the evolved quantum models remain compact while providing competitive performance. We further analyze dataset complexity using twelve structural descriptors and show, across five increasingly challenging meta-learning scenarios, that these measures can reliably predict which quantum architecture will perform best. The results demonstrate perfect or near-perfect predictive accuracy in several scenarios, indicating that complexity metrics offer powerful and compact representations of dataset structure and can effectively guide automated model selection. Overall, this study provides a principled basis for meta-learning-driven quantum architecture design and advances the understanding of how quantum models behave in regression settings--a topic that has received limited exploration in prior work. These findings pave the way for more systematic and theoretically grounded approaches to quantum regression.

quant-pharXiv:2512.19978•Dec 24, 2025•1 citation

Quantum Circuit-Based Learning Models: Bridging Quantum Computing and Machine Learning

Fan Fan, Yilei Shi, Mihai Datcu +5 more

Machine Learning (ML) has been widely applied across numerous domains due to its ability to automatically identify informative patterns from data for various tasks. The availability of large-scale data and advanced computational power enables the development of sophisticated models and training strategies, leading to state-of-the-art performance, but it also introduces substantial challenges. Quantum Computing (QC), which exploits quantum mechanisms for computation, has attracted growing attention and significant global investment as it may address these challenges. Consequently, Quantum Machine Learning (QML), the integration of these two fields, has received increasing interest, with a notable rise in related studies in recent years. We are motivated to review these existing contributions regarding quantum circuit-based learning models for classical data analysis and highlight the identified potentials and challenges of this technique. Specifically, we focus not only on QML models, both kernel-based and neural network-based, but also on recent explorations of their integration with classical machine learning layers within hybrid frameworks. Moreover, we examine both theoretical analysis and empirical findings to better understand their capabilities, and we also discuss the efforts on noise-resilient and hardware-efficient QML that could enhance its practicality under current hardware limitations. In addition, we cover several emerging paradigms for advanced quantum circuit design and highlight the adaptability of QML across representative application domains. This study aims to provide an overview of the contributions made to bridge quantum computing and machine learning, offering insights and guidance to support its future development and pave the way for broader adoption in the coming years.

quant-pharXiv:2602.00048•Artificial Intelligence Review•Jan 20, 2026•2 citations

Quantum Architecture Search for Solving Quantum Machine Learning Tasks

Michael Kölle, Simon Salfer, Tobias Rohe +2 more

Quantum computing leverages quantum mechanics to address computational problems in ways that differ fundamentally from classical approaches. While current quantum hardware remains error-prone and limited in scale, Variational Quantum Circuits offer a noise-resilient framework suitable for today's devices. The performance of these circuits strongly depends on the underlying architecture of their parameterized quantum components. Identifying efficient, hardware-compatible quantum circuit architectures -- known as Quantum Architecture Search (QAS) -- is therefore essential. Manual QAS is complex and error-prone, motivating efforts to automate it. Among various automated strategies, Reinforcement Learning (RL) remains underexplored, particularly in Quantum Machine Learning contexts. This work introduces RL-QAS, a framework that applies RL to discover effective circuit architectures for classification tasks. We evaluate RL-QAS using the Iris and binary MNIST datasets. The agent autonomously discovers low-complexity circuit designs that achieve high test accuracy. Our results show that RL is a viable approach for automated architecture search in quantum machine learning. However, applying RL-QAS to more complex tasks will require further refinement of the search strategy and performance evaluation mechanisms.

arXiv:2509.11198•International Conference on Agents and Artificial Intelligence (ICAART)•Jan 1, 2026•1 citation

Domain-Aware Quantum Circuit for QML

Gurinder Singh, Thaddeus Pellegrini, Kenneth M. Merz,

Designing parameterized quantum circuits (PQCs) that are expressive, trainable, and robust to hardware noise is a central challenge for quantum machine learning (QML) on noisy intermediate-scale quantum (NISQ) devices. We present a Domain-Aware Quantum Circuit (DAQC) that leverages image priors to guide locality-preserving encoding and entanglement via non-overlapping DCT-style zigzag windows. The design employs interleaved encode-entangle-train cycles, where entanglement is applied among qubits hosting neighboring pixels, aligned to device connectivity. This staged, locality-preserving information flow expands the effective receptive field without deep global mixing, enabling efficient use of limited depth and qubits. The design concentrates representational capacity on short-range correlations, reduces long-range two-qubit operations, and encourages stable optimization, thereby mitigating depth-induced and globally entangled barren-plateau effects. We evaluate DAQC on MNIST, FashionMNIST, and PneumoniaMNIST datasets. On quantum hardware, DAQC achieves performance competitive with strong classical baselines (e.g., ResNet-18/50, DenseNet-121, EfficientNet-B0) and substantially outperforming Quantum Circuit Search (QCS) baselines. To the best of our knowledge, DAQC, which uses a quantum feature extractor with only a linear classical readout (no deep classical backbone), currently achieves the best reported performance on real quantum hardware for QML-based image classification tasks. Code and pretrained models are available at: https://github.com/gurinder-hub/DAQC.

quant-pharXiv:2512.17800•Dec 22, 2025•0 citations

Capacity and Architecture in Quantum-Generated Linear Classifiers: An Image Classification Study

Rishi Koushik Reddy Thippireddy, Aswath Babu H

Expectation-value quantum classifiers form a broad class of supervised quantum machine learning models in which predictions are obtained from observables measured on parameterized quantum states. When expressed in a fixed operator basis, these models are equivalent to linear classifiers in an induced feature space, with weights determined by quantum expectation values. Within this setting, the empirical role of architectural design choices remains insufficiently understood.We study how circuit architecture influences performance in quantum-generated linear classifiers for image classification. Classical images are mapped to Pauli feature representations and weight matrices are generated by variational quantum circuits. A full factorial design evaluates five factors: feature representation, circuit capacity (number of circuits K), depth, ansatz family, and initialisation. Additive and interaction effects are quantified using analysis of variance on MNIST and Fashion-MNIST.Results show that capacity contributes primarily through additive logarithmic scaling, while circuit geometry and initialisation determine interaction structure. Feature representation has limited standalone impact but modulates architectural sensitivity. These findings provide a systematic empirical characterisation of architectural behaviour in quantum-generated linear classifiers.

IEEE International Conference on Quantum Control, Computing and Learning (qCCL)•Jun 1, 2026•0 citations
Attributing performance gains in quantum machine learning to genuine quantum resources rather than to classical architectural scaling remains an open methodological challenge. We address this by introducing a counterfactual causal mediation framework that decomposes inter-architectural performance differences into direct effects, attributable to circuit parameterization and expressivity, and indirect effects mediated by quantum information-theoretic observables: entanglement entropy, purity, linear entropy, and quantum mutual information. Applying this framework to five circuit topologies and three benchmark datasets (across 43 validated configurations) reveals that direct architectural contributions systematically exceed quantum-mediated effects, with a mean ratio of 13.1:1 and a mean indirect contribution of 0.82%. These results suggest that current variational quantum circuits operate substantially below their quantum potential, and that principled resource-aware circuit design represents a tractable path toward measurable quantum-mediated performance gains.
We deploy a Quantum Counterfactual Mediation Analysis (QCMA) framework on IBM Quantum processors to ask a precise, hardware-grounded question: are causal regimes identified in noiseless simulation preserved under real quantum noise? Integrating partial quantum state tomography with a linear structural equation model, we decompose inter-architectural performance contrasts into direct effects and indirect quantum-mediated effects across twelve experiments spanning three circuit topologies and two benchmark datasets. Five of six topology-dataset pairs (83%) retain their causal regime when migrating from noiseless simulation to physical hardware. Decoherence inflates quantum-mediated contributions by up to one order of magnitude a noise artefact, not quantum advantage while the Neutral regime dominates both backend. These findings indicate that hardware noise may substantially limit the effective utilization of quantum resources in current NISQ circuits, and motivate further investigation into coherence-preserving circuit design strategies.
The performance of quantum neural network models depends strongly on architectural decisions, including circuit depth, placement of parametrized operations, and data-encoding strategies. Selecting an effective architecture is challenging and closely related to the classical difficulty of choosing suitable neural-network topologies, which is computationally hard. This work investigates automated quantum-circuit construction for regression tasks and introduces a genetic-algorithm framework that discovers Reduced Regressor QNN architectures. The approach explores depth, parametrized gate configurations, and flexible data re-uploading patterns, formulating the construction of quantum regressors as an optimization process. The discovered circuits are evaluated against seventeen classical regression models on twenty-two nonlinear benchmark functions and four analytical functions. Although classical methods often achieve comparable results, they typically require far more parameters, whereas the evolved quantum models remain compact while providing competitive performance. We further analyze dataset complexity using twelve structural descriptors and show, across five increasingly challenging meta-learning scenarios, that these measures can reliably predict which quantum architecture will perform best. The results demonstrate perfect or near-perfect predictive accuracy in several scenarios, indicating that complexity metrics offer powerful and compact representations of dataset structure and can effectively guide automated model selection. Overall, this study provides a principled basis for meta-learning-driven quantum architecture design and advances the understanding of how quantum models behave in regression settings--a topic that has received limited exploration in prior work. These findings pave the way for more systematic and theoretically grounded approaches to quantum regression.
Machine Learning (ML) has been widely applied across numerous domains due to its ability to automatically identify informative patterns from data for various tasks. The availability of large-scale data and advanced computational power enables the development of sophisticated models and training strategies, leading to state-of-the-art performance, but it also introduces substantial challenges. Quantum Computing (QC), which exploits quantum mechanisms for computation, has attracted growing attention and significant global investment as it may address these challenges. Consequently, Quantum Machine Learning (QML), the integration of these two fields, has received increasing interest, with a notable rise in related studies in recent years. We are motivated to review these existing contributions regarding quantum circuit-based learning models for classical data analysis and highlight the identified potentials and challenges of this technique. Specifically, we focus not only on QML models, both kernel-based and neural network-based, but also on recent explorations of their integration with classical machine learning layers within hybrid frameworks. Moreover, we examine both theoretical analysis and empirical findings to better understand their capabilities, and we also discuss the efforts on noise-resilient and hardware-efficient QML that could enhance its practicality under current hardware limitations. In addition, we cover several emerging paradigms for advanced quantum circuit design and highlight the adaptability of QML across representative application domains. This study aims to provide an overview of the contributions made to bridge quantum computing and machine learning, offering insights and guidance to support its future development and pave the way for broader adoption in the coming years.
Quantum computing leverages quantum mechanics to address computational problems in ways that differ fundamentally from classical approaches. While current quantum hardware remains error-prone and limited in scale, Variational Quantum Circuits offer a noise-resilient framework suitable for today's devices. The performance of these circuits strongly depends on the underlying architecture of their parameterized quantum components. Identifying efficient, hardware-compatible quantum circuit architectures -- known as Quantum Architecture Search (QAS) -- is therefore essential. Manual QAS is complex and error-prone, motivating efforts to automate it. Among various automated strategies, Reinforcement Learning (RL) remains underexplored, particularly in Quantum Machine Learning contexts. This work introduces RL-QAS, a framework that applies RL to discover effective circuit architectures for classification tasks. We evaluate RL-QAS using the Iris and binary MNIST datasets. The agent autonomously discovers low-complexity circuit designs that achieve high test accuracy. Our results show that RL is a viable approach for automated architecture search in quantum machine learning. However, applying RL-QAS to more complex tasks will require further refinement of the search strategy and performance evaluation mechanisms.
Designing parameterized quantum circuits (PQCs) that are expressive, trainable, and robust to hardware noise is a central challenge for quantum machine learning (QML) on noisy intermediate-scale quantum (NISQ) devices. We present a Domain-Aware Quantum Circuit (DAQC) that leverages image priors to guide locality-preserving encoding and entanglement via non-overlapping DCT-style zigzag windows. The design employs interleaved encode-entangle-train cycles, where entanglement is applied among qubits hosting neighboring pixels, aligned to device connectivity. This staged, locality-preserving information flow expands the effective receptive field without deep global mixing, enabling efficient use of limited depth and qubits. The design concentrates representational capacity on short-range correlations, reduces long-range two-qubit operations, and encourages stable optimization, thereby mitigating depth-induced and globally entangled barren-plateau effects. We evaluate DAQC on MNIST, FashionMNIST, and PneumoniaMNIST datasets. On quantum hardware, DAQC achieves performance competitive with strong classical baselines (e.g., ResNet-18/50, DenseNet-121, EfficientNet-B0) and substantially outperforming Quantum Circuit Search (QCS) baselines. To the best of our knowledge, DAQC, which uses a quantum feature extractor with only a linear classical readout (no deep classical backbone), currently achieves the best reported performance on real quantum hardware for QML-based image classification tasks. Code and pretrained models are available at: https://github.com/gurinder-hub/DAQC.
Expectation-value quantum classifiers form a broad class of supervised quantum machine learning models in which predictions are obtained from observables measured on parameterized quantum states. When expressed in a fixed operator basis, these models are equivalent to linear classifiers in an induced feature space, with weights determined by quantum expectation values. Within this setting, the empirical role of architectural design choices remains insufficiently understood.We study how circuit architecture influences performance in quantum-generated linear classifiers for image classification. Classical images are mapped to Pauli feature representations and weight matrices are generated by variational quantum circuits. A full factorial design evaluates five factors: feature representation, circuit capacity (number of circuits K), depth, ansatz family, and initialisation. Additive and interaction effects are quantified using analysis of variance on MNIST and Fashion-MNIST.Results show that capacity contributes primarily through additive logarithmic scaling, while circuit geometry and initialisation determine interaction structure. Feature representation has limited standalone impact but modulates architectural sensitivity. These findings provide a systematic empirical characterisation of architectural behaviour in quantum-generated linear classifiers.