arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.07349math.OCcs.SYeess.SY
收藏

鞍点动力学中的稳定性与不稳定性--I部分

Stability and instability in saddle point dynamics -- Part I

Thomas Holding, Ioannis Lestas

摘要:

研究了凹-凸函数通过梯度动力学收敛到一个鞍点的问题。自从Arrow,Hurwicz和Uzawa在[1]中首次提出以来,这种动力学已经广泛地应用于各个领域,然而,也有一些特征使得它们的分析变得不平凡。其中包括缺乏收敛保证时,考虑的功能是不严格的凹凸和次梯度动力学的非光滑性。我们的目的是在这两个部分的文件是提供一个明确的特征一般梯度和次梯度动力学的渐近行为适用于一般凹-凸函数。我们发现,尽管这些动态的非线性和非光滑的$ω$ -极限集是由轨迹,只解决显式线性常微分方程的特点是在纸。更确切地说,在第一部分中提供了一个精确的表征无约束梯度动力学的渐近行为。我们还表明,当收敛到一个鞍点不能保证系统的行为可能是有问题的,任意小的噪声导致一个无界的方差。在第二部分中,我们考虑了一般类的次梯度动力学,限制轨迹在任意凸区域,并表明,当一个平衡点存在的限制轨迹的次梯度动力学的解决方案,只有仿射子空间。后者是一个光滑类的动力学与渐近行为的特点,在第一部分,作为解决方案,明确的线性常微分方程。这些结果被用来制定相应的收敛准则,并证明了与第二部分中提出的几个例子和应用。

英文摘要:

We consider the problem of convergence to a saddle point of a concave-convex function via gradient dynamics. Since first introduced by Arrow, Hurwicz and Uzawa in [1] such dynamics have been extensively used in diverse areas, there are, however, features that render their analysis non trivial. These include the lack of convergence guarantees when the function considered is not strictly concave-convex and also the non-smoothness of subgradient dynamics. Our aim in this two part paper is to provide an explicit characterization to the asymptotic behaviour of general gradient and subgradient dynamics applied to a general concave-convex function. We show that despite the nonlinearity and non-smoothness of these dynamics their $ω$-limit set is comprised of trajectories that solve only explicit linear ODEs that are characterized within the paper. More precisely, in Part I an exact characterization is provided to the asymptotic behaviour of unconstrained gradient dynamics. We also show that when convergence to a saddle point is not guaranteed then the system behaviour can be problematic, with arbitrarily small noise leading to an unbounded variance. In Part II we consider a general class of subgradient dynamics that restrict trajectories in an arbitrary convex domain, and show that when an equilibrium point exists their limiting trajectories are solutions of subgradient dynamics on only affine subspaces. The latter is a smooth class of dynamics with an asymptotic behaviour exactly characterized in Part I, as solutions to explicit linear ODEs. These results are used to formulate corresponding convergence criteria and are demonstrated with several examples and applications presented in Part II.

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。

↑