Deep learning of many-body observables and quantum information scrambling

Abstract

Machine learning has shown significant breakthroughs in quantum science, where in particular deep neural networks exhibited remarkable power in modeling quantum many-body systems. Here, we explore how the capacity of data-driven deep neural networks in learning the dynamics of physical observables is correlated with the scrambling of quantum information. We train a neural network to find a mapping from the parameters of a model to the evolution of observables in random quantum circuits for various regimes of quantum scrambling and test its \textit{generalization} and \textit{extrapolation} capabilities in applying it to unseen circuits. Our results show that a particular type of recurrent neural network is extremely powerful in generalizing its predictions within the system size and time window that it has been trained on for both, localized and scrambled regimes. These include regimes where classical learning approaches are known to fail in sampling from a representation of the full wave function. Moreover, the considered neural network succeeds in \textit{extrapolating} its predictions beyond the time window and system size that it has been trained on for models that show localization, but not in scrambled regimes.

References in corpus (30)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Probing many-body dynamics on a 51-atom quantum simulator
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Quantum many-body systems out of equilibrium
• Characterizing Quantum Supremacy in Near-Term Devices
• Matrix Product States and Projected Entangled Pair States: Concepts, Symmetries, and Theorems
• Operator Spreading in Random Unitary Circuits
• On Many-Body Localization for Quantum Spin Chains
• Controlled exchange interaction between pairs of neutral atoms in an optical lattice
• Quantum Entanglement in Neural Network States
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Neural-Network Approach to Dissipative Quantum Many-Body Dynamics
• Quantum many-body dynamics in two dimensions with artificial neural networks
• Strongly Correlated Materials
• Quantum quenches in the many-body localized phase
• Using a Recurrent Neural Network to Reconstruct Quantum Dynamics of a Superconducting Qubit from Physical Observations
• Dynamical Localization in Disordered Quantum Spin Systems
• Modelling Non-Markovian Quantum Processes with Recurrent Neural Networks
• Transformer Quantum State: A Multi-Purpose Model for Quantum Many-Body Problems
• Quantum dynamics in transverse-field Ising models from classical networks
• Generalized Entanglement Entropies of Quantum Designs
• Neural-network quantum states for many-body physics
• Machine learning time-local generators of open quantum dynamics
• Deep Learning of Quantum Many-Body Dynamics via Random Driving
• Floquet theory for temporal correlations and spectra in time-periodic open quantum systems: Application to squeezed parametric oscillation beyond the rotating-wave approximation
• Deep recurrent networks predicting the gap evolution in adiabatic quantum computing
• Entanglement Area Law for Shallow and Deep Quantum Neural Network States
• Learnability and Complexity of Quantum Samples
• From Architectures to Applications: A Review of Neural Quantum States
• Transfer learning in predicting quantum many-body dynamics: from physical observables to entanglement entropy

Cited by in corpus (7)

• Forecasting long-time dynamics in quantum many-body systems by dynamic mode decomposition
• Hybrid quantum-classical unsupervised data clustering based on the self-organizing feature map
• Synergy between noisy quantum computers and scalable classical deep learning
• Fourier Neural Operators for Time-Periodic Quantum Systems: Learning Floquet Hamiltonians, Observable Dynamics, and Operator Growth
• Artificial intelligence for representing and characterizing quantum systems
• Capturing reduced-order quantum many-body dynamics out of equilibrium via neural ordinary differential equations
• Challenges and opportunities in the supervised learning of quantum circuit outputs