arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1801.00329cs.LGstat.ML
收藏

ZOOpt:用于无导数优化的正则表达式

ZOOpt: Toolbox for Derivative-Free Optimization

Nanjing University(南京大学);East China Normal University(华东师范大学)

Yu-Ren Liu, Yi-Qi Hu, Hong Qian, Chao Qian, Yang Yu

摘要:

无导数优化的最新进展允许有效逼近复杂函数的全局最优解,例如具有许多局部最优值的函数,不可微和非连续函数。本文介绍了ZOOpt(零阶优化)工具箱,该工具箱提供了高效的无导数求解器,并且易于使用。ZOOpt提供基于python核心的单机并行优化,以及通过结合Ray框架(一个著名的构建分布式应用程序的平台)对耗时任务的多机分布式优化。ZOOpt特别关注机器学习中的优化问题,解决高维和噪声问题,如超参数调整和直接策略搜索。工具箱的维护目标是成为现实世界机器学习任务中的即用型工具。

英文摘要:

Recent advances in derivative-free optimization allow efficient approximation of the global-optimal solutions of sophisticated functions, such as functions with many local optima, non-differentiable and non-continuous functions. This article describes the ZOOpt (Zeroth Order Optimization) toolbox that provides efficient derivative-free solvers and is designed easy to use. ZOOpt provides single-machine parallel optimization on the basis of python core and multi-machine distributed optimization for time-consuming tasks by incorporating with the Ray framework -- a famous platform for building distributed applications. ZOOpt particularly focuses on optimization problems in machine learning, addressing high-dimensional and noisy problems such as hyper-parameter tuning and direct policy search. The toolbox is maintained toward a ready-to-use tool in real-world machine learning tasks.

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。

↑