Benchmarking Quantum Extreme Learning based on Gaussian Boson Sampling

• ArXiv number: 2606.15230

Reservoir models offer a hardware-efficient learning paradigm for noisy intermediate-scale quantum devices by exploiting untrained quantum dynamics as a fixed feature map and restricting optimization to a simple classical readout layer. We propose a quantum extreme learning machine implemented using gaussian boson sampling and an encoding strategy that achieves high classification accuracy while reducing optical resource requirements. Classical inputs are jointly encoded in the squeezing parameters and in the interferometer unitary, enabling sampling-based, highly nonlinear feature maps while leveraging large-scale GBS output statistics, which are conjectured to be classically intractable. We systematically compare multiple families of quantum features accessible in the same setup and find that photon-number sampling probabilities provide the best performance, consistent with their higher effective feature dimensionality. Finally, we benchmark against classical nonlinear baselines and analyse robustness under noisy scenarios, showing competitive performance with fewer trainable parameters and indicating practical promise for near-term photonic

• Article complet

Related research projects

QNet

Transport, metastability, and neuromorphic applications in quantum networks

I.P.: Gian Luca Giorgi, Roberta Zambrini

QNet is a European project funded under the call Quantera 2023. The consortium is coordinated by Ticijana Ban from the Institute of Physics, Zagreb, and is also composed of IFISC, Universität des …

CoQuSy-UIB

Complex Quantum Systems: machine learning, thermodynamics, and emergent phenomena

I.P.: Gian Luca Giorgi

CoQuSy is a coordinated project and joins all the researchers at IFISC (belonging either to CSIC or UIB) working in the common line of complex quantum systems. The coordination is motivated by …

Quantum Spain

Quantum Spain

I.P.: Roberta Zambrini

Reserach topic: QUANTUM MACHINE LEARNING Convenio en el BOE: https://www.boe.es/diario_boe/txt.php?id=BOE-A-2023-18333 IFISC participation both as UIB and as CSIC (2 separate budgets)