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 (44)

• Area laws for the entanglement entropy - a review
• Barren plateaus in quantum neural network training landscapes
• Predicting Many Properties of a Quantum System from Very Few Measurements
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• A rigorous and robust quantum speed-up in supervised machine learning
• Chaos and complexity by design
• Harnessing disordered quantum dynamics for machine learning
• Effect of barren plateaus on gradient-free optimization
• Trainability of Dissipative Perceptron-Based Quantum Neural Networks
• Quantum reservoir processing
• Opportunities in Quantum Reservoir Computing and Extreme Learning Machines
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• Boosting computational power through spatial multiplexing in quantum reservoir computing
• Barren plateaus preclude learning scramblers
• Higher Order Derivatives of Quantum Neural Networks with Barren Plateaus
• On barren plateaus and cost function locality in variational quantum algorithms
• Dynamical phase transitions in quantum reservoir computing
• Universal Approximation Property of Quantum Machine Learning Models in Quantum-Enhanced Feature Spaces
• Natural quantum reservoir computing for temporal information processing
• Potential and limitations of quantum extreme learning machines
• Classical surrogates for quantum learning models
• Experimental property-reconstruction in a photonic quantum extreme learning machine
• Trainability barriers and opportunities in quantum generative modeling
• Exponential data encoding for quantum supervised learning
• Quantum reservoir computation utilising scale-free networks
• Microwave signal processing using an analog quantum reservoir computer
• Shadow tomography on general measurement frames
• Role of coherence in many-body Quantum Reservoir Computing
• Quantum simulation of operator spreading in the chaotic Ising model
• Quantum Next Generation Reservoir Computing: An Efficient Quantum Algorithm for Forecasting Quantum Dynamics
• Large-scale quantum reservoir learning with an analog quantum computer
• Latent Style-based Quantum GAN for high-quality Image Generation
• Quantum Extremal Learning
• 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
• Optimal training of finitely-sampled quantum reservoir computers for forecasting of chaotic dynamics
• A Unified Framework for Trace-induced Quantum Kernels
• Quantum reservoir computing using the stabilizer formalism for encoding classical data

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