On fundamental aspects of quantum extreme learning machines

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.

20+21 pages, 9+2 figures

References in corpus (12)

• Microwave signal processing using an analog quantum reservoir computer
• Role of coherence in many-body Quantum Reservoir Computing
• Large-scale quantum reservoir learning with an analog quantum computer
• Latent Style-based Quantum GAN for high-quality Image Generation
• Input-dependence in quantum reservoir computing
• Hybrid quantum-classical reservoir computing for simulating chaotic systems
• Engineering Quantum Reservoirs through Krylov Complexity, Expressivity and Observability
• Assessing Quantum Extreme Learning Machines for Software Testing in Practice
• Photon Number-Resolving Quantum Reservoir Computing
• Quantum reservoir computing using the stabilizer formalism for encoding classical data
• Optimal training of finitely-sampled quantum reservoir computers for forecasting of chaotic dynamics
• A Unified Framework for Trace-induced Quantum Kernels

Cited by in corpus (11)

• Barren Plateaus in Variational Quantum Computing
• Harnessing Quantum Extreme Learning Machines for image classification
• Constrained and Vanishing Expressivity of Quantum Fourier Models
• Efficient quantum-enhanced classical simulation for patches of quantum landscapes
• Quantum Reservoir Computing for Realized Volatility Forecasting
• Engineering Quantum Reservoirs through Krylov Complexity, Expressivity and Observability
• Double descent in quantum kernel methods
• Continuous-variable photonic quantum extreme learning machines for fast collider-data selection
• Optimal quantum reservoir learning in proximity to universality
• Harnessing Quantum Dynamics for Robust and Scalable Quantum Extreme Learning Machines
• Memory-enhanced quantum extreme learning machines for characterizing non-Markovian dynamics