arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.02643cs.LGcs.AI
收藏

极小化可分解次模函数的随机坐标下降法

Random Coordinate Descent Methods for Minimizing Decomposable Submodular Functions

University of Warwick(华威大学)

Alina Ene, Huy L. Nguyen

摘要:

次模函数最小化是在机器学习和计算机视觉中的若干应用中出现的基本优化问题。已知该问题在多项式时间内是可解的,但是通用算法具有高运行时间并且不适合于大规模问题。最近的工作已经使用凸优化技术,以获得非常实用的算法,最小化的功能,是“简单”的功能。在本文中,我们使用随机坐标下降方法,以获得更快的线性收敛速度和更便宜的迭代费用的算法。与交替投影方法相比,我们的算法不依赖于全维向量运算,并且它们在更少的迭代中收敛。

英文摘要:

Submodular function minimization is a fundamental optimization problem that arises in several applications in machine learning and computer vision. The problem is known to be solvable in polynomial time, but general purpose algorithms have high running times and are unsuitable for large-scale problems. Recent work have used convex optimization techniques to obtain very practical algorithms for minimizing functions that are sums of ``simple" functions. In this paper, we use random coordinate descent methods to obtain algorithms with faster linear convergence rates and cheaper iteration costs. Compared to alternating projection methods, our algorithms do not rely on full-dimensional vector operations and they converge in significantly fewer iterations.

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。

↑