2026· IEEE Transactions on Information Forensics and Security· Vol 21, pp. 8138-8150· 0 citations· 39 references
Abstract
We introduce Quantum-KIP, a method that compresses a training set into a small set of kernel inducing points with soft labels. It uses a quantum feature map to compute state-fidelity overlaps and relies only on forward evaluations, avoiding backpropagation through quantum circuits. We provide a compression-induced stability analysis showing that replacing one training example changes the learned set and predictions by $O(m/n)$ . We further provide a joint analysis of this sensitivity bound with intrinsic quantum noise, showing how finite-shot measurement noise and depolarizing noise give rise to privacy-relevant distinguishability bounds for quantum-kernel observations. A circuit-execution analysis shows substantially fewer quantum runs than gradient-based approaches. On MNIST and CIFAR-10 datasets with six-qubit feature maps, Quantum-KIP achieves accuracy close to full-data training, large speedups, reduced privacy leakage, and robustness under depolarizing and measurement noise.
Quantum kernel methods are promising for near-term quantum machine learning, but their training costs are driven by the quadratic scaling of Gram-matrix construction and the measurement cost of estimating individual kernel values. In this work, we investigate one-class anomaly detection as a resource-efficient operatin...
Daniel R. Germain, Benjamin Goldweber, Kayla J. Rodriguez et al.· 0 citations
Results show that FL enables high-performing, privacy-preserving quantum-classical collaboration without centralizing raw data, and achieves this with substantially fewer trainable parameters than the classical neural networks and random forest alternatives.
C. Cano, Daniel M. Jimenez-Gutierrez, Diego Sal et al.· 0 citations
This work develops an observable-based approach to quantum DP tailored to expectation-value estimation from quantum measurements, and introduces a neighboring relation defined directly in terms of observable expectation values and gives general private mechanisms for broad measurement protocols, including classical sha...
Armando Angrisani, Mina Doosti, E. Kashefi· ACM Transactions on Quantum...· 0 citations
KANs offer a promising, efficient, and interpretable machine-learning approach for finite-measurement steering detection of arbitrary two-qubit states, and further feature compression can still retain competitive detection performance.
DF-SQD is introduced, a hybrid algorithm that derives deterministic auxiliary-field circuits from selected double-factorization leaves of the two-electron tensor and is able to discover better results with shallower circuits, is sample efficient, uses configuration recovery and has empirical convergence observation.
A novel physics-guided linear mapper for quantum error mitigation that uses seven distinct interpretable features derived from circuit complexity and device calibration data, which reveals that circuit depth and CNOT count dominate error prediction, consistent with decoherence mechanisms.
Tulsi Chaudhari, Krish Bhatia, Shalini Devendrababu et al.· Lecture Notes in Networks an...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
