arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1602.05908cs.LGstat.ML
收藏

非凸优化问题中逃逸高阶鞍点的有效方法

Efficient approaches for escaping higher order saddle points in non-convex optimization

University of California, Irvine(加州大学欧文分校);Duke University(杜克大学)

Anima Anandkumar, Rong Ge

摘要:

非凸优化问题的局部搜索算法在应用机器学习中很受欢迎。然而,在一般情况下,这是很难保证这样的算法,甚至收敛到局部最小值,由于存在复杂的鞍点结构在高维。许多函数具有退化鞍点,使得一阶和二阶导数不能用局部最优值来区分它们。在本文中,我们使用高阶导数逃脱这些鞍点:我们设计的第一个有效的算法保证收敛到三阶局部最优(而现有的技术是在最多二阶)。我们还表明,这是NP-难的进一步扩展到寻找四阶局部最优。

英文摘要:

Local search heuristics for non-convex optimizations are popular in applied machine learning. However, in general it is hard to guarantee that such algorithms even converge to a local minimum, due to the existence of complicated saddle point structures in high dimensions. Many functions have degenerate saddle points such that the first and second order derivatives cannot distinguish them with local optima. In this paper we use higher order derivatives to escape these saddle points: we design the first efficient algorithm guaranteed to converge to a third order local optimum (while existing techniques are at most second order). We also show that it is NP-hard to extend this further to finding fourth order local optima.

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。

↑