saddle 点动力学的稳定性与不稳定性 第二部分:子梯度方法
Stability and instability in saddle point dynamics Part II: The subgradient method
AI总结:
本文研究了子梯度动力学在任意凸域内的限制,展示了尽管这些动力学具有非线性和非光滑特性,其ω极限集仅由线性微分方程的解组成,并基于此提出了多种收敛性准则和应用示例。
摘要:
在第一部分中,我们考虑了通过梯度动力学收敛到凹凸函数的鞍点问题,并给出了其渐近行为的精确刻画。在第二部分中,我们考虑了一类通用的子梯度动力学,其在任意凸域内进行限制。我们证明,尽管这些动力学具有非线性和非光滑特性,其ω极限集仅由线性微分方程的解组成。特别是,我们证明后者是子梯度动力学在仿射子空间上的解,这是一个光滑的动力学类,其渐近性质已在第一部分中精确刻画。本文还基于这些结果提出了多种收敛性准则,并在全文中讨论了多个示例和应用。
英文摘要:
In part I we considered the problem of convergence to a saddle point of a concave-convex function via gradient dynamics and an exact characterization was given to their asymptotic behaviour. In part II we consider a general class of subgradient dynamics that provide a restriction in an arbitrary convex domain. We show that despite the nonlinear and non-smooth character of these dynamics their $ω$-limit set is comprised of solutions to only linear ODEs. In particular, we show that the latter are solutions to subgradient dynamics on affine subspaces which is a smooth class of dynamics the asymptotic properties of which have been exactly characterized in part I. Various convergence criteria are formulated using these results and several examples and applications are also discussed throughout the manuscript.
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。