arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.04646math.NAcs.NA
收藏

一类预条件时间并行迭代算法的稳定性蕴含鲁棒收敛性

Stability implies robust convergence of a class of preconditioned parallel-in-time iterative algorithms

Shu-Lin Wu, Tao Zhou, Zhi Zhou

摘要:

以时间并行方式求解演化方程是一个很有吸引力的课题,近二十年来提出了许多算法。基于块$α$ -循环预处理技术的算法已经显示出很好的优势,特别是对于波的传播问题。通过快速傅立叶变换分解所涉及的循环矩阵,预处理迭代可以通过所谓的对角化技术有效地计算,这产生了跨所有时间水平的直接并行实现。近年来,人们通过研究迭代矩阵的谱半径来探索预条件迭代的收敛性,这导致了许多基于时间积分器的逐例研究。本文对应用于$u'+Au=f$的算法给出了统一的收敛性分析,其中$σ(A)\subset\mathbb{C}^+$和$σ(A)$是$A\in\mathbb{C}^{m\times m}$的谱.对于任何一个具有稳定性函数$\mathcal{R}(z)$的单步方法(如Runge-Kutta方法),我们证明了全局误差的衰减率受$α/(1-α)$的约束,只要该方法是稳定的,即,$\max_{λ\inσ(A)}|\mathcal{R}(Δtλ)|\leq1$。对于任何线性多步方法,这样的界限变为$cα/(1-cα)$,其中$c\geq1$是由多步方法本身指定的常数。我们的证明仅依赖于时间积分器的稳定性,并且估计与步长$Δt$和谱$σ(A)$无关。

英文摘要:

Solving evolutionary equations in a parallel-in-time manner is an attractive topic and many algorithms are proposed in recent two decades. The algorithm based on the block $α$-circulant preconditioning technique has shown promising advantages, especially for wave propagation problems. By fast Fourier transform for factorizing the involved circulant matrices, the preconditioned iteration can be computed efficiently via the so-called diagonalization technique, which yields a direct parallel implementation across all time levels. In recent years, considerable efforts have been devoted to exploring the convergence of the preconditioned iteration by studying the spectral radius of the iteration matrix, and this leads to many case-by-case studies depending on the used time-integrator. In this paper, we propose a unified convergence analysis for the algorithm applied to $u'+Au=f$, where $σ(A)\subset\mathbb{C}^+$ with $σ(A)$ being the spectrum of $A\in\mathbb{C}^{m\times m}$. For any one-step method (such as the Runge-Kutta methods) with stability function $\mathcal{R}(z)$, we prove that the decay rate of the global error is bounded by $α/(1-α)$, provided the method is stable, i.e., $\max_{λ\inσ(A)}|\mathcal{R}(Δtλ)|\leq1$. For any linear multistep method, such a bound becomes $cα/(1-cα)$, where $c\geq1$ is a constant specified by the multistep method itself. Our proof only relies on the stability of the time-integrator and the estimate is independent of the step size $Δt$ and the spectrum $σ(A)$.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑