A comparative study of different machine learning methods for dissipative quantum dynamics

Abstract

It has been recently shown that supervised machine learning (ML) algorithms can accurately and efficiently predict the long-time populations dynamics of dissipative quantum systems given only short-time population dynamics. In the present article we benchmaked 22 ML models on their ability to predict long-time dynamics of a two-level quantum system linearly coupled to harmonic bath. The models include uni- and bidirectional recurrent, convolutional, and fully-connected feed-forward artificial neural networks (ANNs) and kernel ridge regression (KRR) with linear and most commonly used nonlinear kernels. Our results suggest that KRR with nonlinear kernels can serve as inexpensive yet accurate way to simulate long-time dynamics in cases where the constant length of input trajectories is appropriate. Convolutional Gated Recurrent Unit model is found to be the most efficient ANN model.

arXiv comment22 pages, 6 figures

References in corpus (29)

• Deep Learning in Neural Networks: An Overview
• Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network
• Deep learning for time series classification: a review
• Quantum state engineering with Josephson-junction devices
• QuTiP: An open-source Python framework for the dynamics of open quantum systems
• InceptionTime: Finding AlexNet for Time Series Classification
• LSTM Fully Convolutional Networks for Time Series Classification
• Perspective: Numerically "exact" approach to open quantum dynamics: The hierarchical equations of motion (HEOM)
• Efficient simulation of strong system-environment interactions
• Machine learning for electronically excited states of molecules
• Land Cover Classification via Multi-temporal Spatial Data by Recurrent Neural Networks
• Taming the dynamical sign problem in real-time evolution of quantum many-body problems
• Non-Markovian Dynamical Maps: Numerical Processing of Open Quantum Trajectories
• Inclusion of machine learning kernel ridge regression potential energy surfaces in on-the-fly nonadiabatic molecular dynamics simulation
• Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions
• Memory Effects In Nonequilibrium Quantum Impurity Models
• The quantum phase transition in the sub-ohmic spin-boson model: Quantum Monte-Carlo study with a continuous imaginary time cluster algorithm
• Time-Dependent Density Matrix Renormalization Group Algorithms for Nearly Exact Absorption and Fluorescence Spectra of Molecular Aggregates at Both Zero and Finite Temperature
• Efficient and accurate surface hopping for long time nonadiabatic quantum dynamics
• Sparse polynomial space approach to dissipative quantum systems: Application to the sub-ohmic spin-boson model
• A Unified Stochastic Formulation of Dissipative Quantum Dynamics. I. Generalized Hierarchical Equations
• Modelling Non-Markovian Quantum Processes with Recurrent Neural Networks
• A Unified Stochastic Formulation of Dissipative Quantum Dynamics. II. Beyond Linear Response of Spin Baths
• Machine learning and excited-state molecular dynamics
• Initial System-Environment Correlations via the Transfer Tensor Method
• Stochastic Equation of Motion Approach to Fermionic Dissipative Dynamics. I. Formalism
• Learning quantum dynamics with latent neural ODEs
• One-shot trajectory learning of open quantum systems dynamics
• Stochastic Equation of Motion Approach to Fermionic Dissipative Dynamics. II. Numerical Implementation

Cited by in corpus (11)

• MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflows
• Four-Dimensional-Spacetime Atomistic Artificial Intelligence Models
• QD3SET-1: A Database with Quantum Dissipative Dynamics Data Sets
• Quantum Next Generation Reservoir Computing: An Efficient Quantum Algorithm for Forecasting Quantum Dynamics
• Kernel-based quantum regressor models learn non-Markovianity
• Machine learning meets $\mathfrak{su}(n)$ Lie algebra: Enhancing quantum dynamics learning with exact trace conservation
• Machine learning for predicting control landscape maps of quantum molecular dynamics: Laser-induced three-dimensional alignment of asymmetric top molecules
• Multi-timescale time encoding for CNN prediction of Fenna-Matthews-Olson energy-transfer dynamics
• Compact representation and long-time extrapolation of real-time data for quantum systems using the ESPRIT algorithm
• Toward Quantum-Aware Machine Learning: Improved Prediction of Quantum Dissipative Dynamics via Complex Valued Neural Networks
• Theory of Moment Propagation for Quantum Dynamics in Single-Particle Description