arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1811.02427math.OC
收藏

一种加速复合凸优化的统一自适应张量逼近格式

A Unified Adaptive Tensor Approximation Scheme to Accelerate Composite Convex Optimization

Bo Jiang, Tianyi Lin, Shuzhong Zhang

摘要:

在本文中,我们提出了一个统一的两阶段计划,以加速任何高阶正则张量逼近方法的光滑部分的复合凸优化模型。该方案的优点是不需要假设任何先验知识的Lipschitz常数的梯度,Hessian和/或高阶导数。这是通过在其进展过程中调整算法\textit{adaptively}中使用的参数来实现的,该过程已成功地纳入高阶非凸优化(CartisGouldToint 2018,Birgin-Gardenghi-Martinez-Santos-Toint-2017)。在一般情况下,我们表明,自适应高阶方法的迭代界$O\left( 1 / ε^{1/(p+1)} \right)$,如果一个$p$阶导数信息被用于近似,它具有相同的迭代复杂性,在非自适应版本(Baes-2009,Nesterov-2018),其中Lipschitz常数被假定为已知的,子问题被假定为精确求解。因此,我们的结果部分解决了将自适应策略纳入Nesterov在(Nesterov-2018)中提出的高阶{ \it加速}方法的问题,尽管我们的策略不能确保辅助问题的凸性,并且这种自适应策略已经在高阶非凸优化中流行(CartisGouldToint 2018,Birgin-Gardenghi-Martinez-Santos-Toint-2017)。我们的数值实验结果表明,在一组正则化的逻辑斯谛回归实例中,三次正则化的自适应牛顿法显示出明显的实际加速度效果。

英文摘要:

In this paper, we propose a unified two-phase scheme to accelerate any high-order regularized tensor approximation approach on the smooth part of a composite convex optimization model. The proposed scheme has the advantage of not needing to assume any prior knowledge of the Lipschitz constants for the gradient, the Hessian and/or high-order derivatives. This is achieved by tuning the parameters used in the algorithm \textit{adaptively} in its process of progression, which has been successfully incorporated in high-order nonconvex optimization (CartisGouldToint2018, Birgin-Gardenghi-Martinez-Santos-Toint-2017). In general, we show that the adaptive high-order method has an iteration bound of $O\left( 1 / ε^{1/(p+1)} \right)$ if the first $p$-th order derivative information is used in the approximation, which has the same iteration complexity as in that of the nonadaptive version in (Baes-2009, Nesterov-2018) where the Lipschitz constants are assumed to be known and the subproblems are assumed to be solved exactly. Thus, our results partially address the problem of incorporating adaptive strategies into the high-order {\it accelerated} methods raised by Nesterov in (Nesterov-2018), although our strategies cannot assure the convexity of the auxiliary problem and such adaptive strategies are already popular in high-order nonconvex optimization (CartisGouldToint2018, Birgin-Gardenghi-Martinez-Santos-Toint-2017). Our numerical experiment results show a clear effect of real acceleration displayed in the adaptive Newton's method with cubic regularization on a set of regularized logistic regression instances.

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。

↑