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 1912.08342math.OCcs.LGstat.ML
收藏

基于微分包含的连续时间Optimization算法的收敛性

Finite-Time Convergence of Continuous-Time Optimization Algorithms via Differential Inclusions

Rensselaer Polytechnic Institute(伦斯勒理工学院);Mitsubishi Electrics Research Laboratories(三菱电机研究实验室)

Orlando Romero, Mouhacine Benosman

摘要:

在本文中,我们提出了两个不连续的动力系统在连续时间内保证规定的有限时间局部收敛到严格的局部极小值的给定费用函数。我们的方法包括利用一个基于Lyapunov的微分不等式的微分包含,这导致有限时间稳定性,从而有限时间收敛与可证明的边界上的解决时间。特别地,对于上述微分不等式的精确解,稳定时间界也是精确的,从而实现了规定的有限时间收敛。因此,我们构造了一类不连续的动力系统,二阶的费用函数,作为连续时间优化算法的有限时间收敛和规定的收敛时间。最后,我们说明我们的结果Rosenbrock函数。

英文摘要:

In this paper, we propose two discontinuous dynamical systems in continuous time with guaranteed prescribed finite-time local convergence to strict local minima of a given cost function. Our approach consists of exploiting a Lyapunov-based differential inequality for differential inclusions, which leads to finite-time stability and thus finite-time convergence with a provable bound on the settling time. In particular, for exact solutions to the aforementioned differential inequality, the settling-time bound is also exact, thus achieving prescribed finite-time convergence. We thus construct a class of discontinuous dynamical systems, of second order with respect to the cost function, that serve as continuous-time optimization algorithms with finite-time convergence and prescribed convergence time. Finally, we illustrate our results on the Rosenbrock function.

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。

↑