arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.09449math.OCcs.LG
收藏

线性约束优化问题的Hessian障碍算法

Hessian barrier algorithms for linearly constrained optimization problems

Universität Wien(维也纳大学);Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);Grenoble INP(格勒诺布尔理工学院);Maastricht University(马斯特里赫特大学)

Immanuel M. Bomze, Panayotis Mertikopoulos, Werner Schachinger, Mathias Staudigl

AI总结:

本文提出Hessian障碍算法(HBA),结合Hessian黎曼梯度流前向欧拉离散化与Armijo回溯步长策略,证明其收敛性及收敛率,并通过数值实验验证。

摘要:

在本文中,我们提出了一种用于线性约束优化问题(可能非凸)的内点法。该方法——我们称之为Hessian障碍算法(HBA)——将Hessian黎曼梯度流的前向欧拉离散化与Armijo回溯步长策略相结合。这样,HBA可以被视为镜像下降(MD)的替代方法,并将仿射缩放算法、正则化牛顿过程以及其他几种迭代求解方法作为特例包含在内。我们的主要结果是,在不考虑非退化条件的情况下,该算法收敛到问题的临界点集;因此,在凸情况下,该算法全局收敛到问题的最小集。在线性约束二次规划(不一定凸)的情况下,我们还证明了该方法的收敛率为$\mathcal{O}(1/k^ρ)$,其中$ρ\in(0,1]$仅取决于核函数的选择(即与问题的原语无关)。这些理论结果通过标准非凸测试函数和大规模交通分配问题中的数值实验得到了验证。

英文摘要:

In this paper, we propose an interior-point method for linearly constrained optimization problems (possibly nonconvex). The method - which we call the Hessian barrier algorithm (HBA) - combines a forward Euler discretization of Hessian Riemannian gradient flows with an Armijo backtracking step-size policy. In this way, HBA can be seen as an alternative to mirror descent (MD), and contains as special cases the affine scaling algorithm, regularized Newton processes, and several other iterative solution methods. Our main result is that, modulo a non-degeneracy condition, the algorithm converges to the problem's set of critical points; hence, in the convex case, the algorithm converges globally to the problem's minimum set. In the case of linearly constrained quadratic programs (not necessarily convex), we also show that the method's convergence rate is $\mathcal{O}(1/k^ρ)$ for some $ρ\in(0,1]$ that depends only on the choice of kernel function (i.e., not on the problem's primitives). These theoretical results are validated by numerical experiments in standard non-convex test functions and large-scale traffic assignment problems.

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。

↑