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

Abstract

Accurately modeling quantum dissipative dynamics remains challenging due to environmental complexity and non-Markovian memory effects. Although machine learning provides a promising alternative to conventional simulation techniques, most existing models employ real-valued neural networks (RVNNs) that inherently mismatch the complex-valued nature of quantum mechanics. By decoupling the real and imaginary parts of the density matrix, RVNNs can obscure essential amplitude-phase correlations, compromising physical consistency. Here, we introduce complex-valued neural networks (CVNNs) as a physics-consistent framework for learning quantum dissipative dynamics. CVNNs operate directly on complex-valued inputs, preserve the algebraic structure of quantum states, and naturally encode quantum coherences. Through numerical benchmarks on the spin-boson model and several variants of the Fenna-Matthews-Olson complex, we demonstrate that CVNNs outperform RVNNs in convergence speed, training stability, and physical fidelity -- including significantly improved trace conservation and Hermiticity. These advantages increase with system size and coherence complexity, establishing CVNNs as a robust, scalable, quantum-aware classical approach for simulating open quantum systems in the pre-fault-tolerant quantum era.

References in corpus (36)

• Non-Markovian dynamics in open quantum systems
• Environment-Assisted Quantum Walks in Photosynthetic Energy Transfer
• Quantum theory based on real numbers can be experimentally falsified
• Generalized spin mapping for quantum-classical dynamics
• Ruling out real-valued standard formalism of quantum theory
• 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
• A partially linearized spin-mapping approach for nonadiabatic dynamics. I. Derivation of the theory
• Simulating Open Quantum System Dynamics on NISQ Computers with Generalized Quantum Master Equations
• Do photosynthetic complexes use quantum coherence to increase their efficiency? Probably not
• Tensor-Train Thermo-Field Memory Kernels for Generalized Quantum Master Equations
• Stochastic Representation of Non-Markovian Fermionic Quantum Dissipation
• A partially linearized spin-mapping approach for nonadiabatic dynamics. II. Analysis and comparison with related approaches
• Exact propagation of open quantum systems in a system-reservoir context
• 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
• Artificial-intelligence-based surrogate solution of dissipative quantum dynamics: physics-informed reconstruction of the universal propagator
• QD3SET-1: A Database with Quantum Dissipative Dynamics Data Sets
• MLQD: A package for machine learning-based quantum dissipative dynamics
• Neural Quantum Propagators for Driven-Dissipative Quantum Dynamics
• Non-markovian neural quantum propagator and its application to the simulation of ultrafast nonlinear spectra
• Machine learning meets $\mathfrak{su}(n)$ Lie algebra: Enhancing quantum dynamics learning with exact trace conservation
• Multi-timescale time encoding for CNN prediction of Fenna-Matthews-Olson energy-transfer dynamics