arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.09063math.OC
收藏

带误差的BFGS方法分析

Analysis of the BFGS Method with Errors

Yuchen Xie, Richard Byrd, Jorge Nocedal

摘要:

经典的拟牛顿法的收敛性分析假设每次迭代所用的函数和梯度是精确的。在本文中,我们考虑的情况下,当有(有界)的错误,在这两个计算和建立条件下,轻微修改的BFGS算法与Armijo-沃尔夫线搜索收敛到一个邻域的解决方案,是由错误的大小。我们的一个结果是Byrd,R. H、& Nocedal,J.(1989),它建立了,对于强凸函数,BFGS迭代的一小部分是好的迭代。我们提出的数值结果说明了新的BFGS方法在噪声的存在下的性能。

英文摘要:

The classical convergence analysis of quasi-Newton methods assumes that the function and gradients employed at each iteration are exact. In this paper, we consider the case when there are (bounded) errors in both computations and establish conditions under which a slight modification of the BFGS algorithm with an Armijo-Wolfe line search converges to a neighborhood of the solution that is determined by the size of the errors. One of our results is an extension of the analysis presented in Byrd, R. H., & Nocedal, J. (1989), which establishes that, for strongly convex functions, a fraction of the BFGS iterates are good iterates. We present numerical results illustrating the performance of the new BFGS method in the presence of noise.

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。

↑