Engineering Quantum Reservoirs through Krylov Complexity, Expressivity and Observability

Abstract

This study employs Krylov-based information measures to understand task performance in quantum reservoir computing, a sub-field of quantum machine learning. In our study we show that fidelity and spread complexity can only explain the task performance for short time evolutions of the quantum systems. We then discuss two measures, Krylov expressivity and Krylov observability, and compare them to task performance and the information processing capacity. Our results show that Krylov observability exhibits almost identical behavior to information processing capacity, while being three orders of times faster to compute. In the case when the system is undersampled Krylov observability best captures the behavior of the task performance.

References in corpus (69)

• The effect of data encoding on the expressive power of variational quantum machine learning models
• Quantum Computation as Geometry
• Continuous-variable quantum neural networks
• A Universal Operator Growth Hypothesis
• Harnessing disordered quantum dynamics for machine learning
• Experimental Realization of Quantum Artificial Intelligence
• Quantum chaos and the complexity of spread of states
• Experimental quantum speed-up in reinforcement learning agents
• On The Evolution Of Operator Complexity Beyond Scrambling
• Quantum reservoir processing
• Krylov complexity from integrability to chaos
• Boosting computational power through spatial multiplexing in quantum reservoir computing
• Operator growth and Krylov construction in dissipative open quantum systems
• Krylov Localization and suppression of complexity
• The bulk Hilbert space of double scaled SYK
• Universal chaotic dynamics from Krylov space
• Dynamical phase transitions in quantum reservoir computing
• Quantum Dynamics in Krylov Space: Methods and Applications
• Temporal Information Processing on Noisy Quantum Computers
• Complexity growth of operators in the SYK model and in JT gravity
• Quantum complexity and topological phases of matter
• Probing quantum scars and weak ergodicity-breaking through quantum complexity
• Time Series Quantum Reservoir Computing with Weak and Projective Measurements
• Krylov Complexity in Open Quantum Systems
• Krylov complexity and orthogonal polynomials
• Natural quantum reservoir computing for temporal information processing
• Towards provably efficient quantum algorithms for large-scale machine-learning models
• Krylov Complexity in Free and Interacting Scalar Field Theories with Bounded Power Spectrum
• Krylov complexity and chaos in quantum mechanics
• Information Processing Capacity of Spin-Based Quantum Reservoir Computing Systems
• Hybrid quantum-classical reservoir computing of thermal convection flow
• Operator dynamics in Lindbladian SYK: a Krylov complexity perspective
• A statistical mechanism for operator growth
• Krylov complexity of density matrix operators
• Potential and limitations of quantum extreme learning machines
• Universal relation for operator complexity
• A universal approach to Krylov State and Operator complexities
• Quantum chaos, scrambling and operator growth in $T\bar{T}$ deformed SYK models
• Probing the entanglement of operator growth
• Time evolution of spread complexity in quenched Lipkin-Meshkov-Glick model
• Spread complexity in saddle-dominated scrambling
• Experimental property-reconstruction in a photonic quantum extreme learning machine
• Delay dynamics of neuromorphic optoelectronic nanoscale resonators: Perspectives and applications
• Spread complexity as classical dilaton solutions
• Dissipation as a resource for Quantum Reservoir Computing
• Quantum state complexity meets many-body scars
• On operator growth and emergent Poincaré symmetries
• The Reservoir Learning Power across Quantum Many-Boby Localization Transition
• Feedback-driven quantum reservoir computing for time-series analysis
• A relation between Krylov and Nielsen complexity
• Krylov construction and complexity for driven quantum systems
• On the Interpretability of Quantum Neural Networks
• Insight into Delay Based Reservoir Computing via Eigenvalue Analysis
• Limitations of the recall capabilities in delay based reservoir computing systems
• Krylov Complexity in Lifshitz-type Scalar Field Theories
• Exploring quantum mechanical advantage for reservoir computing
• On fundamental aspects of quantum extreme learning machines
• Spread complexity for measurement-induced non-unitary dynamics and Zeno effect
• Optimizing quantum noise-induced reservoir computing for nonlinear and chaotic time series prediction
• Krylov complexity and Trotter transitions in unitary circuit dynamics
• A double quantum dot memristor
• Explaining Quantum Circuits with Shapley Values: Towards Explainable Quantum Machine Learning
• Solving the time-complexity problem and tuning the performance of quantum reservoir computing by artificial memory restriction
• State estimation with quantum extreme learning machines beyond the scrambling time
• Multiseed Krylov complexity
• Retrieving past quantum features with deep hybrid classical-quantum reservoir computing
• Practical Few-Atom Quantum Reservoir Computing
• Measurable Krylov Spaces and Eigenenergy Count in Quantum State Dynamics
• Diagnosing Quantum Many-body Chaos in Non-Hermitian Quantum Spin Chain via Krylov Complexity

Cited by in corpus (1)

• On fundamental aspects of quantum extreme learning machines