On Fast Simulation of Dynamical System with Neural Vector Enhanced Numerical Solver
This addresses a critical bottleneck in scientific and engineering simulations by enabling faster and more efficient computations, potentially establishing a new paradigm for solving differential equations with deep learning.
The paper tackles the trade-off between accuracy and computational efficiency in simulating dynamical systems by introducing Neural Vector (NeurVec), a deep learning-based corrector that compensates for integration errors to enable larger time steps. NeurVec accelerates traditional solvers by tens to hundreds of times while maintaining high accuracy and stability.
The large-scale simulation of dynamical systems is critical in numerous scientific and engineering disciplines. However, traditional numerical solvers are limited by the choice of step sizes when estimating integration, resulting in a trade-off between accuracy and computational efficiency. To address this challenge, we introduce a deep learning-based corrector called Neural Vector (NeurVec), which can compensate for integration errors and enable larger time step sizes in simulations. Our extensive experiments on a variety of complex dynamical system benchmarks demonstrate that NeurVec exhibits remarkable generalization capability on a continuous phase space, even when trained using limited and discrete data. NeurVec significantly accelerates traditional solvers, achieving speeds tens to hundreds of times faster while maintaining high levels of accuracy and stability. Moreover, NeurVec's simple-yet-effective design, combined with its ease of implementation, has the potential to establish a new paradigm for fast-solving differential equations based on deep learning.