Learning Quantum Operator Dynamics from Short-Time Data
The research proposes a Neural Ordinary Differential Equation (Neural ODE) framework to reconstruct long-time quantum operator dynamics from limited short-time measurements. By expanding observables in Pauli basis and using physics-driven neural networks, the method accurately extrapolates behavior and resolves excitation spectra. This provides a scalable way to extract detailed dynamical information from noisy data on current quantum hardware.