arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.04310stat.MLcs.LG
收藏

求解大规模问题的步长自适应随机拟牛顿法

Stochastic quasi-Newton with adaptive step lengths for large-scale problems

University of Newcastle(纽卡斯尔大学);Uppsala University(乌普萨拉大学)

Adrian Wills, Thomas Schön

摘要:

我们提供了一个强大的数字和快速的方法,能够利用当地的几何形状时,解决大规模的随机优化问题。我们的关键创新是一个辅助变量的建设加上逆海森近似计算使用的迭代和梯度的历史。正是经典的随机梯度算法的马尔可夫链性质使得这种发展成为可能。该结构提供了一种自适应步长的随机线搜索机制。我们对当前最先进的方法进行了数值评估和比较,并在现实世界的基准问题上取得了令人鼓舞的性能,其中观测和未知数的数量为数百万。

英文摘要:

We provide a numerically robust and fast method capable of exploiting the local geometry when solving large-scale stochastic optimisation problems. Our key innovation is an auxiliary variable construction coupled with an inverse Hessian approximation computed using a receding history of iterates and gradients. It is the Markov chain nature of the classic stochastic gradient algorithm that enables this development. The construction offers a mechanism for stochastic line search adapting the step length. We numerically evaluate and compare against current state-of-the-art with encouraging performance on real-world benchmark problems where the number of observations and unknowns is in the order of millions.

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。

↑