arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.08316cs.LG
收藏

一种方差缩减的随机牛顿法

A Variance Reduced Stochastic Newton Method

ETH Zürich(苏黎世联邦理工学院)

Aurelien Lucchi, Brian McWilliams, Thomas Hofmann

摘要:

拟牛顿法在求解凸损失最小化问题中有着广泛的应用。这些方法在各种各样的任务上表现出良好的经验性能,并具有超线性收敛到最优解的特性。对于大规模学习问题,最近提出了随机拟牛顿方法。然而,这些通常仅实现次线性收敛率,并且在实践中没有表现出一贯的良好表现,因为有噪声的Hessian近似会加剧高方差随机梯度估计的影响。在这项工作中,我们提出了Vite,一种新的随机拟牛顿算法,使用现有的一阶技术,以减少这种变化。在不利用具体形式的近似Hessian,我们表明,维特达到最佳的几何速度与恒定的步长时,处理光滑的强凸函数。经验上,我们证明了现有的随机拟牛顿和方差减少随机梯度方法的改进。

英文摘要:

Quasi-Newton methods are widely used in practise for convex loss minimization problems. These methods exhibit good empirical performance on a wide variety of tasks and enjoy super-linear convergence to the optimal solution. For large-scale learning problems, stochastic Quasi-Newton methods have been recently proposed. However, these typically only achieve sub-linear convergence rates and have not been shown to consistently perform well in practice since noisy Hessian approximations can exacerbate the effect of high-variance stochastic gradient estimates. In this work we propose Vite, a novel stochastic Quasi-Newton algorithm that uses an existing first-order technique to reduce this variance. Without exploiting the specific form of the approximate Hessian, we show that Vite reaches the optimum at a geometric rate with a constant step-size when dealing with smooth strongly convex functions. Empirically, we demonstrate improvements over existing stochastic Quasi-Newton and variance reduced stochastic gradient methods.

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。

↑