We are pleased to announce that our paper, “Learning Gaussian Processes with Randomized Quantum Local Kernels,” has been published in International Conference on Quantum Communications, Networking, and Computing (QCNC 2026).

In this work, the authors – Abdallah Aaraba, Soumaya Cherkaoui, Ola Ahmad, Jean-Frédéric Laprade, and Shengrui Wang – introduce a family of local quantum kernels for Gaussian processes (GPs) based on shallow quantum circuits with restricted entanglement and local Pauli measurements. They also propose a randomized mixture-of-kernels framework in which many such local quantum kernels are generated by sampling circuit parameters (via low-discrepancy sequences) and combined through a GP multiple-kernel learning objective. 
Read the full paper on IEEE Xplore:  10.1109/QCNC69040.2026.00108