© 2026 Aqora Quantum S.A.S.

Terms Privacy Legal Notice

arXiv:2603.20167

Quantum inference on a classically trained quantum extreme learning machine

Emanuele Brusaschi, Marco Clementi, Marco Liscidini, Daniele Bajoni, Matteo Galli, Massimo Borghi

quant-phSubmitted Mar 20, 2026• Announced Mar 23, 2026• 0 citations

v1 · Mar 20, 2026 v2 · Aug 7, 2026

Abstract

Quantum extreme learning machines (QELMs) are unconventional computing architectures that bear remarkable promise in both classical and quantum machine-learning tasks, such as the estimate of quantum state properties. However, the probabilistic nature of quantum measurements demands extensive repetitions for training to precisely estimate expectation values, imposing stringent trade-offs among experimental resources, acquisition time, and signal-to-noise ratio, particularly for large datasets. Here we introduce a paradigm shift by harnessing the correspondence between stimulated and spontaneous emission. The QELM is trained exclusively with intense classical fields, yet it performs inference directly on previously unseen quantum input states to predict their quantum properties. This strategy dramatically reduces acquisition times while substantially enhancing the signal-to-noise ratio. Using frequency-bin-encoded biphoton states, implemented here for the first time in a quantum machine-learning architecture, we demonstrate entanglement witnessing of two-qubit states with (93 +- 4)% accuracy, multi-dimensional entanglement detection, and learning of the Hamiltonian governing photon-pair generation with a fidelity of (96 +- 4)%. By establishing classical training as a scalable route to quantum feature extraction, our results bridge macroscopic observables and nonclassical correlations, opening a new pathway toward faster and more robust quantum neural networks

Related papers

Entanglement and classical simulability in quantum extreme-learning machines

A. De Lorenzis, M. P. Casado, Nicola Lo Gullo +3 more

Quantum Machine Learning (QML) has emerged as a promising framework for exploring how quantum dynamics may enhance data processing tasks. Here we investigate Quantum Extreme Learning Machines (QELMs), a quantum analogue of classical Extreme Learning Machines in which training is restricted to the output layer. Our architecture combines dimensionality reduction (via PCA or Autoencoders), quantum state encoding, evolution under an XX Hamiltonian, and projective measurement to produce features for a classical single-layer classifier. By analyzing the classification accuracy as a function of evolution time, we observe a sharp transition between low- and high-accuracy regimes, followed by saturation. Remarkably, the saturated performance is comparable to that obtained using Haar-random unitaries that generate maximally complex dynamics, even though the XX model is integrable and local. Our results indicate that this increase in performance correlates with the onset of entanglement, which improves the embedding of classical data in Hilbert space and leads to more separable clusters in measurement probability space. Thus, moderate entanglement can contribute positively to the structure of the data representation, improving learnability without necessarily implying quantum computational advantage. For the image-classification tasks studied here, namely MNIST, Fashion-MNIST, and CIFAR-10, the relevant evolution time is consistent with information exchange over short distances and, within the explored system sizes, does not show evidence of scaling with the full system size. This suggests that QELM performance in this regime relies only on limited entanglement and remains compatible with efficient classical simulation. Our results clarify how local quantum dynamics and moderate quantum correlations are already sufficient to generate useful feature representations for learning.

arXiv:2509.06873•Physical Review Applied•Apr 23, 2026•1 citation

Efficient classical training of model-free quantum photonic reservoir

Rosario Di Bartolo, Valeria Cimini, Giorgio Minati +10 more

Model-independent estimation of the properties of quantum states is a central challenge in quantum technologies, as experimental imperfections, drifts, and imprecise models of the actual quantum dynamics inevitably hinder accurate reconstructions. Here, we introduce a training strategy for photonic quantum extreme learning machines in which both the learning stage and the optimization of the measurement settings are performed entirely with classical light, while inference is carried out on genuinely quantum states. The protocol is based on the identity between the normalized output intensities following the evolution of coherent states through a linear optical reservoir, and the output statistics obtained with separable input quantum states. Building on this correspondence, we implemented a model-free, gradient-based optimization of the reservoir measurement projection directly on experimental data, without relying on a prior model of the device transformation. We experimentally show that the resulting classical-to-quantum transfer enables accurate reconstruction of single-qubit Pauli observables for previously unseen single-photon states, and extends to the estimation of a two-qubit entanglement witness for arbitrary bipartite states. Beyond demonstrating a qualitatively distinct form of out-of-distribution generalization across the classical-to-quantum boundary, our results identify a practical route to fast, adaptive, and resource-efficient training of photonic quantum learning devices.

quant-pharXiv:2604.12441•Apr 15, 2026•0 citations

Stimulated-emission training of a photonic quantum extreme learning machine

Emanuele Brusaschi, Marco Clementi, Marco Liscidini +3 more

We present a photonic quantum extreme learning machine trained solely with classical light, achieving 93% accuracy in predicting quantum entanglement. This classical trained scheme accelerates learning and increases signal-to-noise ratio by two orders of magnitude.

•Jan 1, 2026•0 citations

Entanglement estimation of Werner states with a quantum extreme learning machine

Hajar Assil, Abderrahim El Allati, Gian Luca Giorgi

Quantum Extreme Learning Machines (QELMs) have emerged as a potent tool for various quantum information processing tasks. We present a QELM protocol for estimating the amount of entanglement in Werner states. The protocol requires the generation of a sequence of random Werner states, which are then combined with a reservoir state and evolved using an Ising Hamiltonian. A set of observables based on the Bloch basis is constructed and employed to train the system to recognize unseen features. To assess the protocol's robustness, noise is introduced into the input states, and the system's performance under these noisy conditions is analyzed. Additionally, the influence of the magnetic field parameter within the Ising Hamiltonian on the estimation accuracy is investigated.

quant-pharXiv:2511.01387•Physical Review A•Nov 4, 2025•7 citations

State estimation with quantum extreme learning machines beyond the scrambling time

Marco Vetrano, Gabriele Lo Monaco, Luca Innocenti +2 more

Quantum extreme learning machines (QELMs) leverage untrained quantum dynamics to efficiently process information encoded in input quantum states, avoiding the high computational cost of training more complicated nonlinear models. On the other hand, quantum information scrambling (QIS) quantifies how the spread of quantum information into correlations makes it irretrievable from local measurements. Here, we explore the tight relation between QIS and the predictive power of QELMs. In particular, we show efficient state estimation is possible even beyond the scrambling time, for many different types of dynamics — in fact, we show that in all the cases we studied, the reconstruction efficiency at long interaction times matches the optimal one offered by random global unitary dynamics. These results offer promising venues for robust experimental QELM-based state estimation protocols, as well as providing novel insights into the nature of QIS from a state estimation perspective.

arXiv:2409.06782•npj Quantum Information•Feb 3, 2025•19 citations

Benchmarking Quantum Extreme Learning based on Gaussian Boson Sampling

Daniel Montesinos, Gian Luca Giorgi, Roberta Zambrini

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 implementations.

quant-pharXiv:2606.15230•Jun 16, 2026•0 citations

Quantum extreme learning machines (QELMs) are unconventional computing architectures that bear remarkable promise in both classical and quantum machine-learning tasks, such as the estimate of quantum state properties. However, the probabilistic nature of quantum measurements demands extensive repetitions for training to precisely estimate expectation values, imposing stringent trade-offs among experimental resources, acquisition time, and signal-to-noise ratio, particularly for large datasets. Here we introduce a paradigm shift by harnessing the correspondence between stimulated and spontaneous emission. The QELM is trained exclusively with intense classical fields, yet it performs inference directly on previously unseen quantum input states to predict their quantum properties. This strategy dramatically reduces acquisition times while substantially enhancing the signal-to-noise ratio. Using frequency-bin-encoded biphoton states, implemented here for the first time in a quantum machine-learning architecture, we demonstrate entanglement witnessing of two-qubit states with (93 +- 4)% accuracy, multi-dimensional entanglement detection, and learning of the Hamiltonian governing photon-pair generation with a fidelity of (96 +- 4)%. By establishing classical training as a scalable route to quantum feature extraction, our results bridge macroscopic observables and nonclassical correlations, opening a new pathway toward faster and more robust quantum neural networks

Quantum Machine Learning (QML) has emerged as a promising framework for exploring how quantum dynamics may enhance data processing tasks. Here we investigate Quantum Extreme Learning Machines (QELMs), a quantum analogue of classical Extreme Learning Machines in which training is restricted to the output layer. Our architecture combines dimensionality reduction (via PCA or Autoencoders), quantum state encoding, evolution under an XX Hamiltonian, and projective measurement to produce features for a classical single-layer classifier. By analyzing the classification accuracy as a function of evolution time, we observe a sharp transition between low- and high-accuracy regimes, followed by saturation. Remarkably, the saturated performance is comparable to that obtained using Haar-random unitaries that generate maximally complex dynamics, even though the XX model is integrable and local. Our results indicate that this increase in performance correlates with the onset of entanglement, which improves the embedding of classical data in Hilbert space and leads to more separable clusters in measurement probability space. Thus, moderate entanglement can contribute positively to the structure of the data representation, improving learnability without necessarily implying quantum computational advantage. For the image-classification tasks studied here, namely MNIST, Fashion-MNIST, and CIFAR-10, the relevant evolution time is consistent with information exchange over short distances and, within the explored system sizes, does not show evidence of scaling with the full system size. This suggests that QELM performance in this regime relies only on limited entanglement and remains compatible with efficient classical simulation. Our results clarify how local quantum dynamics and moderate quantum correlations are already sufficient to generate useful feature representations for learning.

Model-independent estimation of the properties of quantum states is a central challenge in quantum technologies, as experimental imperfections, drifts, and imprecise models of the actual quantum dynamics inevitably hinder accurate reconstructions. Here, we introduce a training strategy for photonic quantum extreme learning machines in which both the learning stage and the optimization of the measurement settings are performed entirely with classical light, while inference is carried out on genuinely quantum states. The protocol is based on the identity between the normalized output intensities following the evolution of coherent states through a linear optical reservoir, and the output statistics obtained with separable input quantum states. Building on this correspondence, we implemented a model-free, gradient-based optimization of the reservoir measurement projection directly on experimental data, without relying on a prior model of the device transformation. We experimentally show that the resulting classical-to-quantum transfer enables accurate reconstruction of single-qubit Pauli observables for previously unseen single-photon states, and extends to the estimation of a two-qubit entanglement witness for arbitrary bipartite states. Beyond demonstrating a qualitatively distinct form of out-of-distribution generalization across the classical-to-quantum boundary, our results identify a practical route to fast, adaptive, and resource-efficient training of photonic quantum learning devices.

Quantum Extreme Learning Machines (QELMs) have emerged as a potent tool for various quantum information processing tasks. We present a QELM protocol for estimating the amount of entanglement in Werner states. The protocol requires the generation of a sequence of random Werner states, which are then combined with a reservoir state and evolved using an Ising Hamiltonian. A set of observables based on the Bloch basis is constructed and employed to train the system to recognize unseen features. To assess the protocol's robustness, noise is introduced into the input states, and the system's performance under these noisy conditions is analyzed. Additionally, the influence of the magnetic field parameter within the Ising Hamiltonian on the estimation accuracy is investigated.

Quantum extreme learning machines (QELMs) leverage untrained quantum dynamics to efficiently process information encoded in input quantum states, avoiding the high computational cost of training more complicated nonlinear models. On the other hand, quantum information scrambling (QIS) quantifies how the spread of quantum information into correlations makes it irretrievable from local measurements. Here, we explore the tight relation between QIS and the predictive power of QELMs. In particular, we show efficient state estimation is possible even beyond the scrambling time, for many different types of dynamics — in fact, we show that in all the cases we studied, the reconstruction efficiency at long interaction times matches the optimal one offered by random global unitary dynamics. These results offer promising venues for robust experimental QELM-based state estimation protocols, as well as providing novel insights into the nature of QIS from a state estimation perspective.

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 implementations.