arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.04906math.OC
收藏

抛物型逼近极小化的线性收敛无约束方法

Linearly Convergent Gradient-Free Methods for Minimization of Parabolic Approximation

Aleksandra Bazarova, Aleksandr Beznosikov, Alexander Gasnikov

摘要:

求非凸函数的全局极小值值是现代最优化中最主要也是最困难的问题之一。在本文的第一部分中,我们考虑了一类“好”的非凸函数,它可以由一个抛物函数上下有界。我们表明,只使用零阶预言,可以获得线性速度$\log \left(\frac{1}{\varepsilon}\right)$找到的全局极小值上的立方体。第二部分的文件看起来在非凸问题略有不同的方式。我们假设最小化二次函数,但同时我们可以访问带有噪声的零阶预言,并且该噪声与到解的距离成正比。在文献中,处理无梯度方法的这种噪声假设是新的。我们表明,在这里也可以实现线性收敛速率。

英文摘要:

Finding the global minimum of non-convex functions is one of the main and most difficult problems in modern optimization. In the first part of the paper, we consider a certain class of "good" non-convex functions that can be bounded above and below by a parabolic function. We show that using only the zeroth-order oracle, one can obtain the linear speed $\log \left(\frac{1}{\varepsilon}\right)$ of finding the global minimum on a cube. The second part of the paper looks at the nonconvex problem in a slightly different way. We assume that minimizing the quadratic function, but at the same time we have access to a zeroth-order oracle with noise and this noise is proportional to the distance to the solution. Dealing with such noise assumptions for gradient-free methods is new in the literature. We show that here it is also possible to achieve the linear rate of convergence.

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。

↑