Sequential-in-time training of nonlinear parametrizations for solving time-dependent partial differential equations
arxiv(2024)
摘要
Sequential-in-time methods solve a sequence of training problems to fit
nonlinear parametrizations such as neural networks to approximate solution
trajectories of partial differential equations over time. This work shows that
sequential-in-time training methods can be understood broadly as either
optimize-then-discretize (OtD) or discretize-then-optimize (DtO) schemes, which
are well known concepts in numerical analysis. The unifying perspective leads
to novel stability and a posteriori error analysis results that provide
insights into theoretical and numerical aspects that are inherent to either OtD
or DtO schemes such as the tangent space collapse phenomenon, which is a form
of over-fitting. Additionally, the unified perspective facilitates establishing
connections between variants of sequential-in-time training methods, which is
demonstrated by identifying natural gradient descent methods on energy
functionals as OtD schemes applied to the corresponding gradient flows.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要