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:2509.16410

Does Data Complexity Predict Quantum Advantage? A framework, a pre-specified test, and an attribution of the measured edge

Christophe Père

Published Sep 19, 2025• 2 citations
arXivHTMLPDF

Abstract

Quantum machine learning (QML) holds promise for pattern recognition, optimization, and data analysis, but the conditions under which it can outperform classical methods remain unclear. We propose data complexity--the structural, statistical, algorithmic, and topological richness of a dataset--as a central axis for stating such conditions, and test the resulting framework under a pre-specified benchmark. The central predictive claim fails. A composite complexity measure does not predict the budget-matched quantum edge across 27 datasets in leave-one-dataset-out validation (pooled R^2=-0.32, versus a pre-specified threshold of 0.4). The failure is strongly coupled to the classical baseline: against logistic regression, the selector reaches R^2=+0.13 and the parity family wins 17% of cells, whereas against the best of six standard classical models performance falls to R^2=-0.94, with parity winning only 1%. The apparent signal therefore tracks classical model error rather than a robust quantum contribution. The tested encoding and reduction procedures further leave little nonlinear headroom for the downstream model to exploit; gradient boosting matches a linear probe across the tested widths. The null is also constrained by the regime: quantum performance is at chance in 81.5% of cells. Yet a deliberately constructed quantum-signature control produces a +0.42 edge under a structure-aware measurement, while generic models required to learn that structure remain near chance. Thus the null result is not evidence that quantum-sensitive structure cannot exist. Rather, in the tested regime, data complexity alone does not predict quantum advantage: the observable edge depends jointly on the classical baseline, accessible data structure, representation and model headroom, and whether quantum-sensitive structure is accessible to the measurement.

DOI
10.48550/arxiv.2509.16410

Related papers

Assessing Claims of Advantage in Quantum Machine Learning: A Critical Review

Stefan Klug, Maximilian Moll

Abstract Quantum machine learning (QML) has attracted growing interest because quantum states and circuits may provide new representational primitives for learning, yet progress remains constrained by noisy intermediate-scale quantum (NISQ) hardware and heterogeneous evaluation practices. This article presents a critical review of recent QML architectures and representative empirical and theoretical studies, with emphasis on work published since 2022 alongside selected seminal references. To improve comparability, “quantum advantage” is assessed in three distinct senses: computational scaling under stated input-access assumptions, empirical predictive performance in the benchmark setting considered, and resource efficiency at a fixed budget accounting for both classical compute and quantum execution, including shot costs. Organized by architecture family and application domain, the review analyzes how baseline strength, hyperparameter optimization, preprocessing, and budget reporting shape conclusions. Overall, quantum feature maps and kernels, as well as variational (often hybrid) pipelines, can be competitive on selected small- to medium-scale benchmarks, but robust end-to-end evidence for a general practical advantage remains limited. Reported gains are often sensitive to budget matching and may be dominated by measurement overheads, dataset and preprocessing effects, and training instabilities. The review concludes that credible progress requires standardized benchmarking, transparent end-to-end resource accounting, and hardware-centered evaluations that test scalability and robustness beyond toy regimes.

•May 7, 2026•0 citations

The Fourier Wall: Why Public Tabular Datasets Refuse Quantum Advantage, and a Certified Recipe for Where It Lives

Javier Mancilla, Tomás Tagliani

Across public tabular benchmarks, quantum machine-learning (QML) models usually lose to carefully tuned classical baselines. We argue that this is a structural property of the datasets rather than merely a limitation of current models. Because an angle-encoded quantum neural network is a partial Fourier series, a genuine advantage can arise only when the target spectrum is simultaneously off-grid, of interaction order at least three, high-frequency, supported by near-independent features, and dense beyond practical enumeration. We call the failure to satisfy these conditions the Fourier wall. We operationalize the conditions as SPECTRA, a two-tier certificate: a simulator-free structural screen followed by a decisive comparison between a matched quantum model and five tuned classical twins using paired-bootstrap confidence bounds. On industrial smart-meter data, SPECTRA correctly refuses the real peak-load target, for which gradient-boosted trees reach a held-out ROC-AUC of 0.999. On the same real energy phases with labels generated by an interacting quantum process, the dynamics-matched quantum model reaches 0.994 versus 0.699 for the best generic classical baseline, and collapses to chance when its interaction couplings are ablated. An exact classical simulator ties the quantum model at small width but incurs measured exponential evaluation cost, with an estimated hardware crossover near 13-19 sites. These results provide a practical recipe for identifying, engineering, and deploying quantum-advantage candidates in tabular data.

quant-pharXiv:2607.15815•Jul 20, 2026•0 citations

Benchmarking Quantum Machine Learning Models Against Classical Deep Learning

Elena Silva, Amelia Horvath

Quantum machine learning (QML) benchmarks frequently compare quantum models against weak classical baselines -- the same methodological gap identified for quantum optimisation in the QCCB study (Popescu and Petrov, 2024). This paper presents the QML-DL Benchmark (QMLDB), a rigorous comparative evaluation of six QML model families against nine state-of-the-art classical deep learning baselines (MLP, CNN, LSTM, ResNet, Transformer, TabNet, XGBoost, LightGBM, CatBoost) across ten benchmark datasets spanning six task domains. QMLDB controls for model capacity, training budget, and data size. QML achieves top performance on three of ten datasets -- all three with strong quantum-process proximity. On the remaining seven, classical deep learning dominates, with Transformer and ResNet consistently outperforming all QML models by 4.8-18.4pp. QMLDB establishes that QML advantage is narrower than commonly claimed, confined to datasets with genuine quantum structure, and proposes a quantum-process proximity score (QPPS) to predict whether a new dataset will benefit from QML before hardware experiments.

Quantum Frontiers Journal•Mar 28, 2025•0 citations

Why Classical-Quantum Machine Learning Works Better Than Classical Machine Learning

Abdullah Md Raihan Chy, Md. Farhan Shahriyar

Quantum machine learning has emerged as a promising paradigm that leverages quantum computational principles to potentially outperform classical approaches on specific learning tasks. This paper presents a comprehensive empirical investigation comparing Quantum Machine Learning (QML), specifically Quantum Support Vector Machines (QSVM) against Classical Machine Learning (CML) baselines including Logistic Regression, K Nearest Neighbors and classical SVMs. We implement quantum kernel methods using variational quantum circuits with angle embedding, IQP and ZZ feature maps on datasets exhibiting varying structural complexity. Our experiments on synthetic quantum generated datasets (Quantum Parity, Quantum Entanglement, Quantum Interference) demonstrate that QSVM achieves superior classification accuracy with improvements ranging from 2.9 % to 60 % over the best classical baselines achieving a 55.6 % overall win rate. Notably, on the Quantum Parity dataset, QSVM consistently outperformed all classical models across multiple configurations. On real-world benchmark datasets (Breast Cancer, Iris, Wine), QSVM Angle achieved 88% accuracy on Breast Cancer compared to 76% for classical SVM Linear a 15.8 % relative improvement while matching the best classical performance on Iris$(100 \%)$and Wine$(92 \%)$. All experiments were conducted using quantum circuit simulation on classical hardware. These results provide empirical evidence that quantum kernel methods offer meaningful advantages over classical approaches on datasets with complex feature interactions. We discuss the theoretical foundations of these improvements including quantum feature space expressivity and kernel alignment.

IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN)•Apr 16, 2026•1 citation

Is data-efficient learning feasible with quantum models?

Alona Sakhnenko, Christian B. Mendl, Jeanette Miriam Lorenz

Abstract The importance of analyzing nontrivial datasets when testing quantum machine learning (QML) models is becoming increasingly prominent in literature, yet a cohesive framework for understanding dataset characteristics remains elusive. In this work, we introduce a data-generation tool that allows to construct semi-artificial classical datasets tailored to quantum kernel methods (QKMs). Using this tool, we show that on fully classical datasets, QKMs can require fewer training examples than classical kernels to reach comparable error, providing clear empirical evidence that data-efficient learning with quantum models is possible on classical data. The main motivation behind this tool is to enable the community to perform controlled studies to figure out which dataset characteristics are particularly fitting for quantum models by tuning the data-generation procedure. Additionally, our study brings a spectral-bias–based generalization metric from classical kernel methods into the QML domain and shows that the performance predicted by this metric aligns closely with empirical results, thereby closing an important gap between theory and practice in QML generalization. Our tool paves the way for a systematic exploration of dataset complexities. This could potentially contribute to a deeper understanding of the generalization benefits of QKM models (extendable to a broader family of QML models) and shifts the search for quantum advantage from ad hoc benchmark hunting to principled dataset design.

arXiv:2508.19437•Quantum Machine Intelligence•Nov 9, 2026•2 citations

How Quantum Is the Advantage? A Fair, Calibration- and Noise-Aware Benchmark and Attribution Audit of Quantum Machine Learning for Network Intrusion Detection

Syeda Anshrah Gillani, Mirza Samad Ahmed Baig, Shahid Munir Shah +2 more

Quantum machine learning (QML) for network intrusion detection (NIDS) is routinely reported to reach near-perfect accuracy, yet the most rigorous studies find that well-tuned classical models remain competitive, and that apparent quantum gains may be artefacts of classical dimensionality reduction and implicit regularisation rather than genuine quantum effects. We ask not whether a quantum model can post a high accuracy, but how quantum the advantage really is. We present a unified, reproducible QML-IDS benchmark evaluating hybrid variational quantum circuits and quantum-kernel SVMs against five honestly-tuned classical baselines across four standard NIDS datasets (NSL-KDD, UNSW-NB15, CICIDS2017, NF-ToN-IoT-v2) under one leakage-controlled protocol, with an equal-budget feature view, imbalance- and calibration-aware metrics with significance testing, and a simulated NISQ noise sweep. We introduce a quantum-attribution audit (parameter-matched classical controls, a random-feature kernel, and a regularisation sweep) that quantifies how much of any gain is genuinely attributable to the quantum component. Tuned classical models (Random Forest, XGBoost) match or exceed the quantum models on aggregate detection on every dataset, and the audit attributes this to classical preprocessing and regularisation rather than quantum effects. Two advantages survive false-discovery-rate correction: the quantum-kernel SVM out-ranks its direct classical surrogate (a random-feature kernel) on AUPRC and ROC-AUC, and a small four-qubit hybrid out-detects the best classical baseline at the 1% false-positive operating point on the distribution-shifted NSL-KDD task (p = 0.005, BH q = 0.030). Code, seeds, and splits are released; our contribution stands whether quantum wins, ties, or loses.

quant-pharXiv:2608.18155•Aug 14, 2026•5 citations
Quantum machine learning (QML) holds promise for pattern recognition, optimization, and data analysis, but the conditions under which it can outperform classical methods remain unclear. We propose data complexity--the structural, statistical, algorithmic, and topological richness of a dataset--as a central axis for stating such conditions, and test the resulting framework under a pre-specified benchmark. The central predictive claim fails. A composite complexity measure does not predict the budget-matched quantum edge across 27 datasets in leave-one-dataset-out validation (pooled R^2=-0.32, versus a pre-specified threshold of 0.4). The failure is strongly coupled to the classical baseline: against logistic regression, the selector reaches R^2=+0.13 and the parity family wins 17% of cells, whereas against the best of six standard classical models performance falls to R^2=-0.94, with parity winning only 1%. The apparent signal therefore tracks classical model error rather than a robust quantum contribution. The tested encoding and reduction procedures further leave little nonlinear headroom for the downstream model to exploit; gradient boosting matches a linear probe across the tested widths. The null is also constrained by the regime: quantum performance is at chance in 81.5% of cells. Yet a deliberately constructed quantum-signature control produces a +0.42 edge under a structure-aware measurement, while generic models required to learn that structure remain near chance. Thus the null result is not evidence that quantum-sensitive structure cannot exist. Rather, in the tested regime, data complexity alone does not predict quantum advantage: the observable edge depends jointly on the classical baseline, accessible data structure, representation and model headroom, and whether quantum-sensitive structure is accessible to the measurement.
Abstract Quantum machine learning (QML) has attracted growing interest because quantum states and circuits may provide new representational primitives for learning, yet progress remains constrained by noisy intermediate-scale quantum (NISQ) hardware and heterogeneous evaluation practices. This article presents a critical review of recent QML architectures and representative empirical and theoretical studies, with emphasis on work published since 2022 alongside selected seminal references. To improve comparability, “quantum advantage” is assessed in three distinct senses: computational scaling under stated input-access assumptions, empirical predictive performance in the benchmark setting considered, and resource efficiency at a fixed budget accounting for both classical compute and quantum execution, including shot costs. Organized by architecture family and application domain, the review analyzes how baseline strength, hyperparameter optimization, preprocessing, and budget reporting shape conclusions. Overall, quantum feature maps and kernels, as well as variational (often hybrid) pipelines, can be competitive on selected small- to medium-scale benchmarks, but robust end-to-end evidence for a general practical advantage remains limited. Reported gains are often sensitive to budget matching and may be dominated by measurement overheads, dataset and preprocessing effects, and training instabilities. The review concludes that credible progress requires standardized benchmarking, transparent end-to-end resource accounting, and hardware-centered evaluations that test scalability and robustness beyond toy regimes.
Across public tabular benchmarks, quantum machine-learning (QML) models usually lose to carefully tuned classical baselines. We argue that this is a structural property of the datasets rather than merely a limitation of current models. Because an angle-encoded quantum neural network is a partial Fourier series, a genuine advantage can arise only when the target spectrum is simultaneously off-grid, of interaction order at least three, high-frequency, supported by near-independent features, and dense beyond practical enumeration. We call the failure to satisfy these conditions the Fourier wall. We operationalize the conditions as SPECTRA, a two-tier certificate: a simulator-free structural screen followed by a decisive comparison between a matched quantum model and five tuned classical twins using paired-bootstrap confidence bounds. On industrial smart-meter data, SPECTRA correctly refuses the real peak-load target, for which gradient-boosted trees reach a held-out ROC-AUC of 0.999. On the same real energy phases with labels generated by an interacting quantum process, the dynamics-matched quantum model reaches 0.994 versus 0.699 for the best generic classical baseline, and collapses to chance when its interaction couplings are ablated. An exact classical simulator ties the quantum model at small width but incurs measured exponential evaluation cost, with an estimated hardware crossover near 13-19 sites. These results provide a practical recipe for identifying, engineering, and deploying quantum-advantage candidates in tabular data.
Quantum machine learning (QML) benchmarks frequently compare quantum models against weak classical baselines -- the same methodological gap identified for quantum optimisation in the QCCB study (Popescu and Petrov, 2024). This paper presents the QML-DL Benchmark (QMLDB), a rigorous comparative evaluation of six QML model families against nine state-of-the-art classical deep learning baselines (MLP, CNN, LSTM, ResNet, Transformer, TabNet, XGBoost, LightGBM, CatBoost) across ten benchmark datasets spanning six task domains. QMLDB controls for model capacity, training budget, and data size. QML achieves top performance on three of ten datasets -- all three with strong quantum-process proximity. On the remaining seven, classical deep learning dominates, with Transformer and ResNet consistently outperforming all QML models by 4.8-18.4pp. QMLDB establishes that QML advantage is narrower than commonly claimed, confined to datasets with genuine quantum structure, and proposes a quantum-process proximity score (QPPS) to predict whether a new dataset will benefit from QML before hardware experiments.
Quantum machine learning has emerged as a promising paradigm that leverages quantum computational principles to potentially outperform classical approaches on specific learning tasks. This paper presents a comprehensive empirical investigation comparing Quantum Machine Learning (QML), specifically Quantum Support Vector Machines (QSVM) against Classical Machine Learning (CML) baselines including Logistic Regression, K Nearest Neighbors and classical SVMs. We implement quantum kernel methods using variational quantum circuits with angle embedding, IQP and ZZ feature maps on datasets exhibiting varying structural complexity. Our experiments on synthetic quantum generated datasets (Quantum Parity, Quantum Entanglement, Quantum Interference) demonstrate that QSVM achieves superior classification accuracy with improvements ranging from 2.9 % to 60 % over the best classical baselines achieving a 55.6 % overall win rate. Notably, on the Quantum Parity dataset, QSVM consistently outperformed all classical models across multiple configurations. On real-world benchmark datasets (Breast Cancer, Iris, Wine), QSVM Angle achieved 88% accuracy on Breast Cancer compared to 76% for classical SVM Linear a 15.8 % relative improvement while matching the best classical performance on Iris(100%)(100 \%)(100%)and Wine(92%)(92 \%)(92%). All experiments were conducted using quantum circuit simulation on classical hardware. These results provide empirical evidence that quantum kernel methods offer meaningful advantages over classical approaches on datasets with complex feature interactions. We discuss the theoretical foundations of these improvements including quantum feature space expressivity and kernel alignment.
Abstract The importance of analyzing nontrivial datasets when testing quantum machine learning (QML) models is becoming increasingly prominent in literature, yet a cohesive framework for understanding dataset characteristics remains elusive. In this work, we introduce a data-generation tool that allows to construct semi-artificial classical datasets tailored to quantum kernel methods (QKMs). Using this tool, we show that on fully classical datasets, QKMs can require fewer training examples than classical kernels to reach comparable error, providing clear empirical evidence that data-efficient learning with quantum models is possible on classical data. The main motivation behind this tool is to enable the community to perform controlled studies to figure out which dataset characteristics are particularly fitting for quantum models by tuning the data-generation procedure. Additionally, our study brings a spectral-bias–based generalization metric from classical kernel methods into the QML domain and shows that the performance predicted by this metric aligns closely with empirical results, thereby closing an important gap between theory and practice in QML generalization. Our tool paves the way for a systematic exploration of dataset complexities. This could potentially contribute to a deeper understanding of the generalization benefits of QKM models (extendable to a broader family of QML models) and shifts the search for quantum advantage from ad hoc benchmark hunting to principled dataset design.
Quantum machine learning (QML) for network intrusion detection (NIDS) is routinely reported to reach near-perfect accuracy, yet the most rigorous studies find that well-tuned classical models remain competitive, and that apparent quantum gains may be artefacts of classical dimensionality reduction and implicit regularisation rather than genuine quantum effects. We ask not whether a quantum model can post a high accuracy, but how quantum the advantage really is. We present a unified, reproducible QML-IDS benchmark evaluating hybrid variational quantum circuits and quantum-kernel SVMs against five honestly-tuned classical baselines across four standard NIDS datasets (NSL-KDD, UNSW-NB15, CICIDS2017, NF-ToN-IoT-v2) under one leakage-controlled protocol, with an equal-budget feature view, imbalance- and calibration-aware metrics with significance testing, and a simulated NISQ noise sweep. We introduce a quantum-attribution audit (parameter-matched classical controls, a random-feature kernel, and a regularisation sweep) that quantifies how much of any gain is genuinely attributable to the quantum component. Tuned classical models (Random Forest, XGBoost) match or exceed the quantum models on aggregate detection on every dataset, and the audit attributes this to classical preprocessing and regularisation rather than quantum effects. Two advantages survive false-discovery-rate correction: the quantum-kernel SVM out-ranks its direct classical surrogate (a random-feature kernel) on AUPRC and ROC-AUC, and a small four-qubit hybrid out-detects the best classical baseline at the 1% false-positive operating point on the distribution-shifted NSL-KDD task (p = 0.005, BH q = 0.030). Code, seeds, and splits are released; our contribution stands whether quantum wins, ties, or loses.