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 1210.6403math.OC
收藏

一种无导数的CoMirror算法

A Derivative-Free CoMirror Algorithm

Heinz H. Bauschke, Warren L. Hare, Walaa M. Moursi

摘要:

我们考虑$\min\{f(x):g(x) \le 0, ~x\in X\},$,其中$X$是$\RR^m$的紧凸子集,$f$和$g$是定义在$X$的开邻域上的连续凸函数。我们在无导数优化的设置中工作,假设$f$和$g$通过黑盒提供,该黑盒仅提供用于函数的较低$\mathcal{C}^2$表示的函数值。我们提出了一个衍生物的$\eps$ -comirror算法\cite{BBTGBT2010}的优化变体。数学收敛取决于准确地近似次梯度的能力较低的$\mathcal{C}^2$功能,我们证明是可能的,通过线性插值。我们提供了收敛性分析,量化迭代的函数值和最优函数值之间的差异。我们发现,我们开发的DFO算法具有相同的收敛结果,原来的基于梯度的算法。我们提出了一些数值测试,证明了该算法的实际可行性,并得出结论,为进一步的研究方向。

英文摘要:

We consider $\min\{f(x):g(x) \le 0, ~x\in X\},$ where $X$ is a compact convex subset of $\RR^m$, and $f$ and $g$ are continuous convex functions defined on an open neighbourhood of $X$. We work in the setting of derivative-free optimization, assuming that $f$ and $g$ are available through a black-box that provides only function values for a lower-$\mathcal{C}^2$ representation of the functions. We present a derivative-free optimization variant of the $\eps$-comirror algorithm \cite{BBTGBT2010}. Algorithmic convergence hinges on the ability to accurately approximate subgradients of lower-$\mathcal{C}^2$ functions, which we prove is possible through linear interpolation. We provide convergence analysis that quantifies the difference between the function values of the iterates and the optimal function value. We find that the DFO algorithm we develop has the same convergence result as the original gradient-based algorithm. We present some numerical testing that demonstrate the practical feasibility of the algorithm, and conclude with some directions for further research.

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。

↑