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.
Generalization in quantum machine learnin g from few training data
9 Pith papers cite this work, alongside 392 external citations. Polarity classification is still indexing.
9
Pith papers citing it
392
external citations · Crossref
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
Fixed upload circuits approximate tunable ones to error ε with depth O_σ[(log(1/ε))^σ] for any σ>1 (improving prior polynomial bounds) and matching Ω(log(1/ε)) lower bounds for mismatch-class targets via auxiliary extensions and Turán-Nazarov analysis.
MCTS discovers superior data encoding circuits for QCCNNs that outperform standard encodings on medical datasets, with effective rank of feature maps serving as a performance predictor.
Local tensor-train surrogates approximate quantum machine learning models via Taylor polynomials and tensor networks, delivering polynomial parameter scaling and explicit generalization bounds controlled by patch radius.
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.
Proposes projected quantum kernels with misspecified GP bandit algorithms and regret bounds to trade off expressivity against learnability in quantum kernel optimization.
Survey of quantum feature encoding families with a cost-expressivity-robustness taxonomy, closed-form NISQ bounds, and a five-regime decision framework that recommends shallow angle encodings when gate error rate p is at or above 10^-3.
Extends Fano bounds to sufficiency of low conditional entropy and defines a quantum entanglement task for infinite-dimensional systems with bounds via maximal singlet fraction of finite-dimensional approximations.
QCNN, QRNN, and QViT perform well on low-feature data but degrade on high-feature datasets, with QViT most robust to quantum noise and classical-style models better against adversarial noise.
citing papers explorer
-
Local tensor-train surrogates for quantum learning models
Local tensor-train surrogates approximate quantum machine learning models via Taylor polynomials and tensor networks, delivering polynomial parameter scaling and explicit generalization bounds controlled by patch radius.
-
A Comprehensive Analysis of Accuracy and Robustness in Quantum Neural Networks
QCNN, QRNN, and QViT perform well on low-feature data but degrade on high-feature datasets, with QViT most robust to quantum noise and classical-style models better against adversarial noise.