Breaking concentration barriers for quantum extreme learning on digital quantum processors
Timothée Dao, Ege Yilmaz, Ibrahim Shehzad, Christophe Pere, Kumar Ghosh, Isabelle Wittmann, Thomas Brunschwiler, Giorgio Cortiana, Corey O'Meara, Stefan Woerner, Francesco Tacchino
quant-phSubmitted Mar 13, 2026• Announced Mar 16, 2026• 0 citations
Reservoir computing leverages rich, non-linear dynamics to process temporal data. Quantum variants promise enhanced expressivity from high-dimensional Hilbert spaces, yet their practical applicability is hindered by hardware noise and concentration effects that can erase input-output distinguishability at large system sizes. In this work, we present and experimentally demonstrate a Quantum Extreme Learning Machine (QELM) tailored to state-of-the-art superconducting platforms, employing up to 124 qubits and circuits with more than 5,000 two-qubit gates on IBM Quantum computers. We introduce a practical multi-objective hyperparameter tuning strategy that jointly monitors observable variability, capacity, and task performance to identify noise-robust operating points. In addition, we develop a local eigentask analysis that enables computationally efficient feature selection and effective information retrieval. We report evidence of a regime of optimality that is identifiable at small scales and transferable across tasks and larger systems, and we achieve performances competitive with leading classical baselines on representative benchmarks for time-series forecasting and satellite image classification. Together, our results establish a viable and robust framework for large-scale, pre-fault-tolerant quantum machine learning and provide a foundation for extending reservoir-based methods to more expressive architectures and real-world scenarios.
Reservoir computing leverages rich, non-linear dynamics to process temporal data. Quantum variants promise enhanced expressivity from high-dimensional Hilbert spaces, yet their practical applicability is hindered by hardware noise and concentration effects that can erase input-output distinguishability at large system sizes. In this work, we present and experimentally demonstrate a Quantum Extreme Learning Machine (QELM) tailored to state-of-the-art superconducting platforms, employing up to 124 qubits and circuits with more than 5,000 two-qubit gates on IBM Quantum computers. We introduce a practical multi-objective hyperparameter tuning strategy that jointly monitors observable variability, capacity, and task performance to identify noise-robust operating points. In addition, we develop a local eigentask analysis that enables computationally efficient feature selection and effective information retrieval. We report evidence of a regime of optimality that is identifiable at small scales and transferable across tasks and larger systems, and we achieve performances competitive with leading classical baselines on representative benchmarks for time-series forecasting and satellite image classification. Together, our results establish a viable and robust framework for large-scale, pre-fault-tolerant quantum machine learning and provide a foundation for extending reservoir-based methods to more expressive architectures and real-world scenarios.
Abstract Quantum extreme learning machines (QELMs) have emerged as a promising framework for quantum machine learning. Their appeal lies in the rich feature map induced by the dynamics of a quantum substrate—the quantum reservoir—and the efficient post-measurement training via linear regression. Here, we study the expressivity of QELMs by decomposing the prediction of QELMs into a Fourier series. We show that the achievable Fourier frequencies are determined by the data encoding scheme, while Fourier coefficients depend on both the reservoir and the measurement. Notably, the expressivity of QELMs is fundamentally limited by the number of Fourier frequencies and the number of observables, while the complexity of the prediction hinges on the reservoir. As a cautionary note on scalability, we identify four sources that can lead to the exponential concentration of the observables as the system size grows (randomness, hardware noise, entanglement, and global measurements) and show how this can turn QELMs into useless input-agnostic oracles. In particular, our result on the reservoir-induced concentration strongly indicates that quantum reservoirs drawn from a highly random ensemble make QELM models unscalable. Our analysis elucidates the potential and fundamental limitations of QELMs and lays the groundwork for systematically exploring quantum reservoir systems for other machine learning tasks.
Quantum learning provides a versatile paradigm for information processing by exploiting the intrinsic representational capacity of high-dimensional Hilbert spaces. Here, we investigate a Hamiltonian-encoding framework for quantum reservoir computing that simultaneously addresses three key challenges in quantum learning: trainability, hardware efficiency, and information stability. In this framework, input data are directly mapped onto a fixed Hamiltonian and transformed into expressive nonlinear features through quantum dynamical evolution. By employing the reservoir-computing paradigm, the approach naturally circumvents the barren plateau problem in quantum learning landscapes. We validate the framework across two complementary platforms: an analog superconducting array processor and a digital gate-based quantum circuit implementation. Despite their fundamentally different realizations, both platforms exhibit comparable representational power and achieve competitive learning performance, establishing a unified framework for cross-platform quantum learning. While both implementations achieve comparable performance, the analog processor may offer a more hardware-efficient realization by bypassing the temporal overhead of gate-based decomposition and thereby making more effective use of finite coherence times, albeit at the expense of universality. Furthermore, we find that finite dissipation suppresses quantum-scrambling-induced instabilities at long evolution times and can enhance learning performance, revealing a constructive role for environmental coupling in stabilizing quantum learning dynamics. Collectively, these results establish Hamiltonian-encoded reservoir computing as a compact, expressive, and hardware-efficient paradigm for quantum learning on current-generation quantum platforms.
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.
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.
Quantum reservoir computers (QRCs) have emerged as a promising approach to quantum machine learning, since they utilize the natural dynamics of quantum systems for data processing and are simple to train. Here, we consider n-qubit quantum extreme learning machines (QELMs) with initial-state encoding and continuous-time reservoir dynamics. Applying the Pauli transfer matrix (PTM) formalism reveals the encoding-generated features and their linear transformation by quantum channels, and thereby provides a nonlinear vector autoregression model as an interpretable classical representation of a QELM. We show that the nonlinear information processing capacity of a QELM factorizes into the ability of the encoding to represent a given target function and the decodability of the relevant Pauli features after the effective PTM. Comparing geometric and statistical decodability reveals features that are algebraically hidden yet recoverable through data correlations. We relate the decodability of Pauli features to the spreading of measurement operators under Heisenberg evolution (Krylov growth). Focusing on the unitary channel, we discuss how structured Hamiltonians, when paired with certain observables, can impair model performance, as reflected in a low rank of the readout and the effective PTMs. We trace this effect to Hamiltonian symmetries and derive asymptotic rank estimates for symmetry-resolved observable families. Our decodability analysis disentangles the contributions of encoding, reservoir dynamics, and measurement observables, and thus provides interpretable diagnostics that can inform the design of QELMs and reduce reliance on exhaustive hyperparameter search. As a specific application, we consider forecasting nonlinear dynamical systems and show that the readout of a trained QELM closely matches the expression of the underlying flow map at leading orders.
In this thesis we investigate the information processing capabilities of Quantum Extreme Learning Machines and discuss their real world applications in the field of astrophysics, particularly for atmospheric retrieval of exoplanets and supernovae spectral analysis, designing noise resilient models for Noise Intermediate Scale Quantum (NISQ) implementations. Extreme Learning Machines (ELMs) offer rapid training and structural efficiency by utilizing a randomized hidden layer—the reservoir—to map input data into a high-dimensional feature space, effectively linearizing complex learning problems. While traditionally implemented via randomized classical neural networks, the mathematical properties of these reservoirs naturally extend to complex physical systems. This universality has driven the development of Quantum Extreme Learning Machines (QELMs), which utilize quantum systems as the computational reservoir. In the field of physical extreme learning machines, information is processed through the internal dynamics of the system and recollected by measuring the system. In the context of QELMs, this consists in selecting a set of observables or a POVM to be measured on the reservoir, whose outcomes is then used to train the post-processing layer.In this work, we will first review the foundations of Neural Networs, ELMs and Reservoir Computers, highlighting specifically on similarities and fundamental differences between these models and develop the theory behind the quantum counterparts. Then, we demonstrate that QELMs can efficiently process and estimate quantum states well beyond the reservoir's scrambling time, beyond which the information should be irretrievable through local measurements. Furthermore, we show that within this regime, specific classes of Hamiltonians achieve reconstruction accuracies matching those of global random unitary dynamics. Following these theoretical aspects, we design noise-resilient QELM architectures tailored for the spectral analysis of complex astrophysical phenomena. We apply these models to exoplanetary atmospheric retrieval and supernova remnant datasets, particularly deploying the algorithm for the exoplanetary context on real quantum hardware (IBM Fez). By evaluating various pre-processing and encoding strategies—including Dense Angle Encoding, IQP embedding, and Data Re-uploading—we demonstrate that these noise-resilient QELMs are highly adaptable to different classes of astrophysical objects and capable of extracting critical spectral parameters also on NISQ devices, paving the way for real world applications of Quantum Computing in the astrophysical field.