arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.12883math.OCcs.LGmath.DS
收藏

Rosenbrock函数的闭环梯度下降算法

A closed loop gradient descent algorithm applied to Rosenbrock's function

Australian National University(澳大利亚国立大学)

Subhransu Bhattacharjee, Ian Petersen

摘要:

我们介绍了一种新的自适应阻尼技术的惯性梯度系统的应用程序作为梯度下降算法无约束优化。在一个例子中,使用非凸Rosenbrock的功能,我们表现出现有的动量为基础的梯度优化方法的改进。还使用李雅普诺夫稳定性分析,我们证明了该算法的连续时间版本的性能。使用数值模拟,我们认为它的离散时间对应的性能,通过使用辛欧拉法的离散化。

英文摘要:

We introduce a novel adaptive damping technique for an inertial gradient system which finds application as a gradient descent algorithm for unconstrained optimisation. In an example using the non-convex Rosenbrock's function, we show an improvement on existing momentum-based gradient optimisation methods. Also using Lyapunov stability analysis, we demonstrate the performance of the continuous-time version of the algorithm. Using numerical simulations, we consider the performance of its discrete-time counterpart obtained by using the symplectic Euler method of discretisation.

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。

↑