A coherence law based on the readout-visible aligned coherence rate (a Rayleigh quotient of the noise generator) predicts gradient survival in noisy U(1)-equivariant QNNs, with simulations confirming R²=0.979 and a special channel test showing no loss where predicted.
Supervised Learning with Quantum-Enhanced Feature Spaces.Nature2019,567, 209–212
22 Pith papers cite this work, alongside 2,360 external citations. Polarity classification is still indexing.
22
Pith papers citing it
2,360
external citations · OpenAlex
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
QRSI spans degenerate quantum eigenspaces almost surely by conjugating the Hamiltonian with random unitaries on g parallel branches and using subspace estimation, while exactly preserving the spectral gap.
Quantum circuits for coherent multilayer neural network inference achieve quadratic to polylogarithmic speedups over classical methods depending on quantum data access models for inputs and weights.
All embedding quantum kernels can be understood as entangled tensor kernels, yielding new insights into their inductive bias and potential dequantization.
QML-PipeGuard is a framework for runtime behavioral fingerprinting of QML pipelines that absorbs benign drift while detecting adversarial channel substitution via informationally complete measurements.
A necessary condition for variational quantum circuits to reach exact ground states requires matching module projection norms between input and solution, enabling classical O(n^5) exact solvers for problems like MaxCut.
A new QNN architecture with unified graph, HAL, and ONNX pipeline enables cross-framework and cross-hardware QML with training time within 8% of native implementations and identical accuracy on Iris, Wine, and MNIST-4 tasks.
A Pretty Good Measurement classifier reformulates multi-class radiomics as quantum state discrimination and achieves competitive performance on NSCLC subtyping and PCa risk tasks.
Proposes projected quantum kernels with misspecified GP bandit algorithms and regret bounds to trade off expressivity against learnability in quantum kernel optimization.
Learning-induced spectral structure in hybrid quantum models is diagnosed by edge-resolved two-boson interference correlated with Fiedler cuts and by absolute Bloch drift that separates anomalies from benign states.
A variational quantum autoencoder detects anomalies in brain MRI by scoring resistance to compression, reporting slice-level ROC-AUC of 0.95 and outperforming classical autoencoders and PCA on public datasets.
QADR decomposes n-qubit VQCs into local sub-circuits to reduce memory from O(2^n) to O(n * 2^{2d+1}) and mitigate barren plateaus, scaling to 2000 features on MNIST and wind turbine diagnostics while matching classical models.
Benchmark of quantum-inspired encodings shows they provide no reliable machine-learning advantage over classical methods on classical datasets due to their geometric properties.
Classical reconstruction, not quantum execution, is the dominant per-query cost in circuit-cut QNN training (median 53% at three cuts), capping achievable speed-up while leaving accuracy and robustness roughly intact on Iris and MNIST.
Graph neural network achieves AUC of 0.883 for up versus anti-up quark jet charge discrimination in controlled QCD simulations.
For noisy near-term quantum devices, the paper recommends shallow angle encoding over amplitude encoding once two-qubit error rates exceed roughly 10^-3.
Hybrid XGBoost plus data-reuploading quantum model shows modest F1 gain and lowest false-alarm rate in proxy-free evaluation on temporally partitioned TLM:UAV data, framed as incremental NISQ-era benefit.
A quantum-inspired ARIMA pipeline using swap-test correlations and variational circuits is proposed, but its validation is confounded by order selection and a missing same-order classical baseline.
A hybrid geometric classifier using correlation groups and overlap similarities achieves 0.85-0.96 accuracy on standard tabular datasets and 0.85 minority recall on highly imbalanced fraud data via a variational quantum refinement layer.
Quantum machine learning models do not surpass classical baselines in prediction performance, policy stability, or training time, though they may help filter noise and control false positives.
Hybriqu Encoder delivers 5.4% faster pure angle encoding at 64 qubits on Apple Silicon by using AVX SIMD and cache-friendly precalculations, with gains increasing beyond L1 cache size while full-state updates remain memory-bound.
The paper introduces 'Platonic Projection Structures,' a reformulation of standard PSD operator theory applied to representation learning, with experiments that verify definitions rather than test predictions.
citing papers explorer
-
A Coherence Law for Trainability in Noisy Equivariant Quantum Neural Networks
A coherence law based on the readout-visible aligned coherence rate (a Rayleigh quotient of the noise generator) predicts gradient survival in noisy U(1)-equivariant QNNs, with simulations confirming R²=0.979 and a special channel test showing no loss where predicted.
-
Quantum Randomized Subspace Iteration
QRSI spans degenerate quantum eigenspaces almost surely by conjugating the Hamiltonian with random unitaries on g parallel branches and using subspace estimation, while exactly preserving the spectral gap.
-
Accelerating Inference for Multilayer Neural Networks with Quantum Computers
Quantum circuits for coherent multilayer neural network inference achieve quadratic to polylogarithmic speedups over classical methods depending on quantum data access models for inputs and weights.
-
New perspectives on quantum kernels through the lens of entangled tensor kernels
All embedding quantum kernels can be understood as entangled tensor kernels, yielding new insights into their inductive bias and potential dequantization.
-
QML-PipeGuard: Drift-Aware Behavioral Fingerprinting for Quantum Machine Learning Pipeline Integrity
QML-PipeGuard is a framework for runtime behavioral fingerprinting of QML pipelines that absorbs benign drift while detecting adversarial channel substitution via informationally complete measurements.
-
Reachability Constraints in Variational Quantum Circuits: Optimization within Polynomial Group Module
A necessary condition for variational quantum circuits to reach exact ground states requires matching module projection norms between input and solution, enabling classical O(n^5) exact solvers for problems like MaxCut.
-
Eliminating Vendor Lock-In in Quantum Machine Learning via Framework-Agnostic Neural Networks
A new QNN architecture with unified graph, HAL, and ONNX pipeline enables cross-framework and cross-hardware QML with training time within 8% of native implementations and identical accuracy on Iris, Wine, and MNIST-4 tasks.
-
Pretty Good Measurement for Radiomics: A Quantum-Inspired Multi-Class Classifier for Lung Cancer Subtyping and Prostate Cancer Risk Stratification
A Pretty Good Measurement classifier reformulates multi-class radiomics as quantum state discrimination and achieves competitive performance on NSCLC subtyping and PCa risk tasks.
-
Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization
Proposes projected quantum kernels with misspecified GP bandit algorithms and regret bounds to trade off expressivity against learnability in quantum kernel optimization.
-
Spectral Geometry and Bosonic-Bloch Probes: Explorations in Quantum Learning
Learning-induced spectral structure in hybrid quantum models is diagnosed by edge-resolved two-boson interference correlated with Fiedler cuts and by absolute Bloch drift that separates anomalies from benign states.
-
Compression-Driven Anomaly Detection in Brain MRI Using an Interpretable Quantum Autoencoder
A variational quantum autoencoder detects anomalies in brain MRI by scoring resistance to compression, reporting slice-level ROC-AUC of 0.95 and outperforming classical autoencoders and PCA on public datasets.
-
Quantum Algorithm for Distributed Reduction of Entanglements (QADR): A Trainable and Simulation-Efficient QML Framework
QADR decomposes n-qubit VQCs into local sub-circuits to reduce memory from O(2^n) to O(n * 2^{2d+1}) and mitigate barren plateaus, scaling to 2000 features on MNIST and wind turbine diagnostics while matching classical models.
-
A Matched Spectral Benchmark of Quantum Inspired Feature Maps
Benchmark of quantum-inspired encodings shows they provide no reliable machine-learning advantage over classical methods on classical datasets due to their geometric properties.
-
DistributedEstimator: Distributed Training of Quantum Neural Networks via Circuit Cutting
Classical reconstruction, not quantum execution, is the dominant per-query cost in circuit-cut QNN training (median 53% at three cuts), capping achievable speed-up while leaving accuracy and robustness roughly intact on Iris and MNIST.
-
Application of Deep Learning to Jet Charge Discrimination
Graph neural network achieves AUC of 0.883 for up versus anti-up quark jet charge discrimination in controlled QCD simulations.
-
Feature Encoding in Quantum Machine Learning: A Survey and Practical Guidelines
For noisy near-term quantum devices, the paper recommends shallow angle encoding over amplitude encoding once two-qubit error rates exceed roughly 10^-3.
-
Quantum Machine Learning for Cyber-Physical Anomaly Detection in Unmanned Aerial Vehicles: A Leakage-Free Evaluation with Proxy-Audited Feature Sets
Hybrid XGBoost plus data-reuploading quantum model shows modest F1 gain and lowest false-alarm rate in proxy-free evaluation on temporally partitioned TLM:UAV data, framed as incremental NISQ-era benefit.
-
QARIMA: A Quantum Approach To Classical Time Series Analysis
A quantum-inspired ARIMA pipeline using swap-test correlations and variational circuits is proposed, but its validation is confounded by order selection and a missing same-order classical baseline.
-
Quantum-Inspired Geometric Classification with Correlation Group Structures and VQC Decision Modeling
A hybrid geometric classifier using correlation groups and overlap similarities achieves 0.85-0.96 accuracy on standard tabular datasets and 0.85 minority recall on highly imbalanced fraud data via a variational quantum refinement layer.
-
Quantum vs. Classical Machine Learning: A Unified Empirical Comparison
Quantum machine learning models do not surpass classical baselines in prediction performance, policy stability, or training time, though they may help filter noise and control false positives.
-
Accelerating Quantum State Encoding with SIMD: Design, Implementation, and Benchmarking
Hybriqu Encoder delivers 5.4% faster pure angle encoding at 64 qubits on Apple Silicon by using AVX SIMD and cache-friendly precalculations, with gains increasing beyond L1 cache size while full-state updates remain memory-bound.
-
Platonic Projection Structures: Operator-Induced Observability in Representation Learning
The paper introduces 'Platonic Projection Structures,' a reformulation of standard PSD operator theory applied to representation learning, with experiments that verify definitions rather than test predictions.