arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.06751math.OC
收藏

积分方法与加速Optimization算法

Integration Methods and Accelerated Optimization Algorithms

Damien Scieur, Vincent Roulet, Francis Bach, Alexandre d'Aspremont

摘要:

我们表明,加速最优化方法可以看作是特殊情况下的多步积分计划从数值分析,适用于梯度流方程。在这方面的最新进展相比,这里考虑的微分方程是基本的梯度流,我们表明,多步计划允许集成这个微分方程使用较大的步长,从而直观地解释加速结果。

英文摘要:

We show that accelerated optimization methods can be seen as particular instances of multi-step integration schemes from numerical analysis, applied to the gradient flow equation. In comparison with recent advances in this vein, the differential equation considered here is the basic gradient flow and we show that multi-step schemes allow integration of this differential equation using larger step sizes, thus intuitively explaining acceleration results.

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。

↑