arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1601.04738math.OCcs.LGstat.ML
收藏

子采样牛顿法II:局部收敛速度

Sub-Sampled Newton Methods II: Local Convergence Rates

International Computer Science Institute(国际计算机科学研究所);University of California at Berkeley(加州大学伯克利分校)

Farbod Roosta-Khorasani, Michael W. Mahoney

摘要:

许多数据拟合应用需要解决涉及大量高维参数函数之和的最优化问题。在这里,我们考虑的问题,最小化的总和$n$功能的凸约束集$\mathcal{X} \subseteq \mathbb{R}^{p}$,其中$n$和$p$是大的。在这样的问题中,子采样作为减少$n$的一种方式可以提供大量的计算效率。在二阶方法的背景下,我们首先给出定量的局部收敛结果的牛顿的方法的Hessian是均匀子采样的变体。使用随机矩阵浓度不等式,可以以保持曲率信息的方式进行子采样。使用这种子采样策略,我们建立了局部Q-线性和Q-超线性收敛速率。我们还给出了额外的收敛结果时,通过修改其频谱或Levenberg型正则化的子采样海森。最后,除了Hessian子采样之外,我们还考虑对梯度进行子采样,以进一步降低每次迭代的计算复杂性。我们使用随机数值线性代数(RandNLA)的近似矩阵乘法结果来获得适当的采样策略,我们建立局部R-线性收敛速率。在这样的设置中,我们还表明,一个非常积极的样本量增加的结果在R-超线性收敛算法。虽然样本大小取决于问题的条件数,但我们的收敛速度与问题无关,即,它们不依赖于与问题相关的量。因此,我们这里的分析可以用来补充我们的基本框架的结果,从同伴的论文,[38],通过探索算法的权衡,在实践中是重要的。

英文摘要:

Many data-fitting applications require the solution of an optimization problem involving a sum of large number of functions of high dimensional parameter. Here, we consider the problem of minimizing a sum of $n$ functions over a convex constraint set $\mathcal{X} \subseteq \mathbb{R}^{p}$ where both $n$ and $p$ are large. In such problems, sub-sampling as a way to reduce $n$ can offer great amount of computational efficiency. Within the context of second order methods, we first give quantitative local convergence results for variants of Newton's method where the Hessian is uniformly sub-sampled. Using random matrix concentration inequalities, one can sub-sample in a way that the curvature information is preserved. Using such sub-sampling strategy, we establish locally Q-linear and Q-superlinear convergence rates. We also give additional convergence results for when the sub-sampled Hessian is regularized by modifying its spectrum or Levenberg-type regularization. Finally, in addition to Hessian sub-sampling, we consider sub-sampling the gradient as way to further reduce the computational complexity per iteration. We use approximate matrix multiplication results from randomized numerical linear algebra (RandNLA) to obtain the proper sampling strategy and we establish locally R-linear convergence rates. In such a setting, we also show that a very aggressive sample size increase results in a R-superlinearly convergent algorithm. While the sample size depends on the condition number of the problem, our convergence rates are problem-independent, i.e., they do not depend on the quantities related to the problem. Hence, our analysis here can be used to complement the results of our basic framework from the companion paper, [38], by exploring algorithmic trade-offs that are important in practice.

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。

↑