arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1712.08571math.OC
收藏

关于BFGS在一类分段线性非光滑函数上的收敛性

On the convergence of BFGS on a class of piecewise linear non-smooth functions

Yuchen Xie, Andreas Waechter

摘要:

拟牛顿Broyden-Fletcher-Goldfarb-Shanno(BFGS)方法自20世纪60年代问世以来,已被证明是求解光滑目标函数最小化问题的可靠而有效的方法。最近,据经验观察,当与Armijo-Wolfe线搜索相结合时,它对非光滑问题也非常有效,但迄今为止只能建立非常有限的理论收敛理论。在本文中,我们扩展这些结果考虑凸分段线性函数的两个片,是不是下有界。我们证明了该算法总是终止于有限次数的迭代,最终产生一个无界的方向。换句话说,与梯度法相反,BFGS算法不会收敛到非静止点。

英文摘要:

The quasi-Newton Broyden-Fletcher-Goldfarb-Shanno (BFGS) method has proven to be very reliable and efficient for the minimization of smooth objective functions since its inception in the 1960s. Recently, it was observed empirically that it also works remarkably well for non-smooth problems when combined with the Armijo-Wolfe line search, but only very limited theoretical convergence theory could be established so far. In this paper, we expand these results by considering convex piecewise linear functions with two pieces that are not bounded below. We prove that the algorithm always terminates in a finite number of iterations, eventually generating an unbounded direction. In other words, in contrast to the gradient method, the BFGS algorithm does not converge to a non-stationary point.

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。

↑