arXiv Machine Learning July 23, 2026 By Kilian Tscharke, Pascal Debus

A Multiclass Quantum Aligned Centroid Kernel

Read the original on arXiv Machine Learning →

arXiv:2607. 19782v1 Announce Type: cross Abstract: Kernel methods are powerful tools in machine learning but commonly used full-Gram kernels face three key limitations: (1) quadratic scaling with training set size; (2) the use of fixed, non-trainable kernels; and (3) the absence of an intrinsic formulation for multiclass classification.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 13

Is data-efficient learning feasible with quantum models?

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.

By Alona Sakhnenko, Christian B. Mendl, Jeanette M. Lorenz

benchmarks safety

arXiv Machine Learning

Jul 8

Benign Overfitting with Quantum Kernels

arXiv:2503. 17020v2 Announce Type: replace-cross Abstract: Kernel methods compare inputs through feature maps.

By Joachim Tomasi, Sandrine Anthoine, Hachem Kadri

arXiv Machine Learning

Sep 22

Comparative Study of Quantum and Classical Machine Learning Models in Binary Classification

arXiv:2609.23476v1 Announce Type: cross Abstract: A potential path forward is Quantum Machine Learning (QML), which aims to leverage quantum computing in conjunction with classical machine learning t...

By Anand Kumar Mishra, Ramanuj Awasthi

arXiv Machine Learning

Jun 9

Quantum feature-map learning with reduced resource overhead

arXiv:2510. 03389v2 Announce Type: replace-cross Abstract: Current quantum computers require algorithms that use limited resources economically.

By Jonas J\"ager, Philipp Els\"asser, Elham Torabian

efficiency benchmarks

arXiv Machine Learning

Jul 2

Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization

arXiv:2607. 01080v1 Announce Type: new Abstract: We investigate Gaussian process (GP) bandit optimization with quantum kernels, assuming the mean reward function lies in the reproducing kernel Hilbert space (RKHS) induced by the quantum kernel.

By Yuqi Huang, Vincent Y. F. Tan, Sharu Theresa Jose

reinforcement-learning

arXiv AI

Aug 12

Regression and Classification with Single-Qubit Quantum Neural Networks

arXiv:2412. 09486v2 Announce Type: replace-cross Abstract: The literature reflects a mutually beneficial relationship between machine learning and quantum computing, where progress in one field frequently drives improvements in the other.

By Leandro C. Souza, Bruno C. Guingo, Gilson Giraldi, Renato Portugal

One email a morning, machine-written

Related stories

Is data-efficient learning feasible with quantum models?

Benign Overfitting with Quantum Kernels

Comparative Study of Quantum and Classical Machine Learning Models in Binary Classification

Quantum feature-map learning with reduced resource overhead

Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization

Regression and Classification with Single-Qubit Quantum Neural Networks