arXiv:2604. 06135v2 Announce Type: replace-cross Abstract: Efficient data loading remains a bottleneck for near-term quantum machine learning.
The paper introduces Neural Fourier Surrogates (NFS), a stochastic classical neural network that learns coefficients over a finite Fourier series support similar to quantum neural networks (QNNs). By testing on tabular benchmark datasets, NFS demonstrates competitive classification performance against established classical baselines and data‑reuploading QNNs. The authors also compare the learned Fourier spectra of QNNs and NFS on synthetic data, positioning NFS as a natural classical baseline for evaluating QNN performance.
Quantum computing promises new capabilities beyond classical computation. Mid-circuit measurements (MCMs) enable error correction and outcome-dependent control, but their reliability is limited by noi...
arXiv:2308. 11290v2 Announce Type: replace-cross Abstract: Understanding the dynamics of large quantum systems is hindered by the curse of dimensionality.
arXiv:2607. 09113v1 Announce Type: cross Abstract: Data scarcity and class imbalance are persistent challenges in machine learning that degrade model generalization and introduce predictive bias.
Circuit cutting lets a large quantum neural network (QNN) run as independent subcircuits on small devices, but rebuilding its outputs by reconstruction carries a classical sampling overhead exponential in the number of cuts - the dominant runtime cost in prior work. We ask whether, for machine-learning tasks, this step is necessary, and replace it with late fusion: each subcircuit is trained and measured independently, and a small classical head combines their outputs - a linear-cost, decision-level combination borrowed from multimodal learning.
Amplitude embedding lets a variational quantum model read many classical features with few qubits, but the model output is then only a quadratic form in the normalized input. Data re-uploading, which...
arXiv:2508. 19437v2 Announce Type: replace-cross 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.
The paper investigates how parameterized quantum circuits can incorporate task‑aligned inductive biases by encoding a fixed, task‑defined spectral query alongside a signal that varies between samples. By modulating the combination of existing signal frequencies, the query changes the circuit’s hypothesis class without adding new sample‑dependent information, aligning the circuit with tasks based on nonuniform Fourier transforms. Experiments on small‑scale spectral and radar‑inspired classification tasks show that aligned queries improve learning from limited data compared to circuits with mismatched or absent queries.
arXiv:2606. 26312v1 Announce Type: cross Abstract: Autoencoders transformed classical machine learning by solving the curse of dimensionality, enabling principled weight initialization and learning compact, structured representations.
arXiv:2607. 21409v1 Announce Type: cross Abstract: A central challenge in quantum machine learning is understanding the scaling behavior of parameterized quantum circuits (PQCs).
arXiv:2606. 03517v1 Announce Type: cross Abstract: Training quantum neural networks (QNNs) on quantum hardware is currently bottlenecked by the cost of gradient estimation: standard parameter-shift methods require a number of circuit evaluations that grows quadratically with the number of trainable parameters, making hardware-based optimisation impractical beyond small system sizes.