Potential and limitations of quantum extreme learning machines

Abstract

Quantum reservoir computers (QRC) and quantum extreme learning machines (QELM) aim to efficiently post-process the outcome of fixed -- generally uncalibrated -- quantum devices to solve tasks such as the estimation of the properties of quantum states. The characterisation of their potential and limitations, which is currently lacking, will enable the full deployment of such approaches to problems of system identification, device performance optimization, and state or process reconstruction. We present a framework to model QRCs and QELMs, showing that they can be concisely described via single effective measurements, and provide an explicit characterisation of the information exactly retrievable with such protocols. We furthermore find a close analogy between the training process of QELMs and that of reconstructing the effective measurement characterising the given device. Our analysis paves the way to a more thorough understanding of the capabilities and limitations of both QELMs and QRCs, and has the potential to become a powerful measurement paradigm for quantum state estimation that is more resilient to noise and imperfections.

12 pages, 7 figures, comments welcome

References in corpus (8)

• Time Series Quantum Reservoir Computing with Weak and Projective Measurements
• Experimental single-setting quantum state tomography
• Reconstructing quantum states with quantum reservoir networks
• Creating and concentrating quantum resource states in noisy environments using a quantum neural network
• Quantum reservoir computing in finite dimensions
• Dynamical learning of a photonics quantum-state engineering process
• Enhanced detection techniques of Orbital Angular Momentum states in the classical and quantum regimes
• Regression of high dimensional angular momentum states of light

Cited by in corpus (32)

• Experimental property-reconstruction in a photonic quantum extreme learning machine
• Quantum machine learning with Adaptive Boson Sampling via post-selection
• On fundamental aspects of quantum extreme learning machines
• Exploring quantum mechanical advantage for reservoir computing
• Shadow tomography on general measurement frames
• Tackling Sampling Noise in Physical Systems for Machine Learning Applications: Fundamental Limits and Eigentasks
• Harnessing Quantum Extreme Learning Machines for image classification
• State estimation with quantum extreme learning machines beyond the scrambling time
• Retrieving past quantum features with deep hybrid classical-quantum reservoir computing
• Practical Few-Atom Quantum Reservoir Computing
• Quantum Extreme Learning of molecular potential energy surfaces and force fields
• Quantum reservoir computing for photonic entanglement witnessing
• Entanglement estimation of Werner states with a quantum extreme learning machine
• An operational definition of quantum information scrambling
• Robust Quantum Reservoir Computing for Molecular Property Prediction
• Demonstration of Hardware Efficient Photonic Variational Quantum Algorithm
• Estimating many properties of a quantum state via quantum reservoir processing
• Quantum memristor with vacuum--one-photon qubits
• Experimental demonstration of enhanced quantum tomography via quantum reservoir processing
• Quantum simulations of complex systems
• Engineering Quantum Reservoirs through Krylov Complexity, Expressivity and Observability
• Generating Quantum Reservoir State Representations with Random Matrices
• Benchmarking of quantum fidelity kernels for Gaussian process regression
• Double descent in quantum kernel methods
• Harnessing Quantum Dynamics for Robust and Scalable Quantum Extreme Learning Machines
• Edge of Many-Body Quantum Chaos in Quantum Reservoir Computing
• Continuous-variable photonic quantum extreme learning machines for fast collider-data selection
• Practical Quantum Reservoir Computing in Rydberg Atom Arrays
• Quantum reservoir computing for predicting and characterizing chaotic maps
• Optical Quantum Computing
• Memory-enhanced quantum extreme learning machines for characterizing non-Markovian dynamics
• Classification of quantum states of light using random measurements through a multimode fiber