Machine learning meets $\mathfrak{su}(n)$ Lie algebra: Enhancing quantum dynamics learning with exact trace conservation

Abstract

Machine learning (ML) has emerged as a promising tool for simulating quantum dissipative dynamics. However, existing methods often struggle to enforce key physical constraints, such as trace conservation, when modeling reduced density matrices (RDMs). While Physics-Informed Neural Networks (PINN) aim to address these challenges, they frequently fail to achieve full physical consistency. In this work, we introduce a novel approach that leverages the $\mathfrak{su}(n)$ Lie algebra to represent RDMs as a combination of an identity matrix and $n^2-1$ Hermitian, traceless, and orthogonal basis operators,where $n$ is the system's dimension. By learning only the coefficients associated with this basis, our framework inherently ensures exact trace conservation, as the traceless nature of the basis restricts the trace contribution solely to the identity matrix. This eliminates the need for explicit trace-preserving penalty terms in the loss function, simplifying optimization and improving learning efficiency. We validate our approach on two benchmark quantum systems: the spin-boson model and the Fenna-Matthews-Olson complex. By comparing the performance of four neural network (NN) architectures -- Purely Data-driven Physics-Uninformed Neural Networks (PUNN), $\mathfrak{su}(n)$ Lie algebra-based PUNN ($\mathfrak{su}(n)$-PUNN), traditional PINN, and $\mathfrak{su}(n)$ Lie algebra-based PINN ($\mathfrak{su}(n)$-PINN) -- we highlight the limitations of conventional methods and demonstrate the superior accuracy, robustness, and efficiency of our approach in learning quantum dissipative dynamics.

References in corpus (32)

• Non-Markovian dynamics in open quantum systems
• Environment-Assisted Quantum Walks in Photosynthetic Energy Transfer
• Generalized spin mapping for quantum-classical dynamics
• Taming Quantum Noise for Efficient Low Temperature Simulations of Open Quantum Systems
• Spin-mapping approach for nonadiabatic molecular dynamics
• A mapping approach to surface hopping
• Universal Prony fitting decomposition for optimized hierarchical quantum master equations
• Long-time Low-latency Quantum Memory by Dynamical Decoupling
• Unified Formulation of Phase Space Mapping Approaches for Nonadiabatic Quantum Dynamics
• Physics-informed neural networks for quantum control
• A partially linearized spin-mapping approach for nonadiabatic dynamics. I. Derivation of the theory
• Do photosynthetic complexes use quantum coherence to increase their efficiency? Probably not
• Simulating Open Quantum System Dynamics on NISQ Computers with Generalized Quantum Master Equations
• Tensor-Train Thermo-Field Memory Kernels for Generalized Quantum Master Equations
• Stochastic Representation of Non-Markovian Fermionic Quantum Dissipation
• Exact propagation of open quantum systems in a system-reservoir context
• A partially linearized spin-mapping approach for nonadiabatic dynamics. II. Analysis and comparison with related approaches
• Quantum Transport from the Perspective of Quantum Open Systems
• A partially linearized spin-mapping approach for simulating nonlinear optical spectra
• A comparative study of different machine learning methods for dissipative quantum dynamics
• Stochastic Equation of Motion Approach to Fermionic Dissipative Dynamics. I. Formalism
• Fewest-Switches Surface Hopping with Long Short-Term Memory Networks
• Stochastic Equation of Motion Approach to Fermionic Dissipative Dynamics. II. Numerical Implementation
• Simulation of absorption spectra of molecular aggregates: a Hierarchy of Stochastic Pure States approach
• On detailed balance in nonadiabatic dynamics: From spin spheres to equilibrium ellipsoids
• Exact generator and its high order expansions in the time-convolutionless generalized master equation: Applications to the spin-boson model and exictation energy transfer
• Four-Dimensional-Spacetime Atomistic Artificial Intelligence Models
• Extended dissipaton equation of motion for electronic open quantum systems: Application to the Kondo impurity model
• QD3SET-1: A Database with Quantum Dissipative Dynamics Data Sets
• Artificial-intelligence-based surrogate solution of dissipative quantum dynamics: physics-informed reconstruction of the universal propagator
• Neural Quantum Propagators for Driven-Dissipative Quantum Dynamics
• Non-markovian neural quantum propagator and its application to the simulation of ultrafast nonlinear spectra

Cited by in corpus (1)

• Toward Quantum-Aware Machine Learning: Improved Prediction of Quantum Dissipative Dynamics via Complex Valued Neural Networks