arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.08181math.OCcs.CCcs.NAmath.NA
收藏

一类多重极小问题的无导数全局极小化

Derivative-free global minimization for a class of multiple minima problems

Xiaopeng Luo, Xin Xu, Daoyi Dong

摘要:

我们证明了基于有限差分的无导数下降(FD-DFD)方法有能力找到一类多重极小问题的全局极小点。我们的主要结果表明,对于一类由具有Lipschitz连续梯度的强凸函数扩展的多重极小目标,FD-DFD的迭代收敛于全局极小点$x_*$,且对固定的$0<ρ<1$和任意初始迭代$x_1\in\mathbb{R}^d$,当参数选择适当时,都具有线性收敛性$\|x_{k+1}-x_*\|_2^2\leqslantρ^k \|x_1-x_*\|_2^2$.由于每次迭代的成本,即,函数求值的数目是固定的,并且几乎与维度$d$无关,FD-DFD算法具有用于找到点$x$的复杂度界限$\mathcal{O}(\log\frac{1}ε)$,使得最优性间隙$\|x-x_*\|_2^2$小于$ε>0$。从$5$到$500$的不同维数的数值实验证明了FD-DFD方法的优点。

英文摘要:

We prove that the finite-difference based derivative-free descent (FD-DFD) methods have a capability to find the global minima for a class of multiple minima problems. Our main result shows that, for a class of multiple minima objectives that is extended from strongly convex functions with Lipschitz-continuous gradients, the iterates of FD-DFD converge to the global minimizer $x_*$ with the linear convergence $\|x_{k+1}-x_*\|_2^2\leqslantρ^k \|x_1-x_*\|_2^2$ for a fixed $0<ρ<1$ and any initial iteration $x_1\in\mathbb{R}^d$ when the parameters are properly selected. Since the per-iteration cost, i.e., the number of function evaluations, is fixed and almost independent of the dimension $d$, the FD-DFD algorithm has a complexity bound $\mathcal{O}(\log\frac{1}ε)$ for finding a point $x$ such that the optimality gap $\|x-x_*\|_2^2$ is less than $ε>0$. Numerical experiments in various dimensions from $5$ to $500$ demonstrate the benefits of the FD-DFD method.

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。

↑