arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.03043math.OC
收藏

正则化经验风险最小化的分布式块对角逼近方法

Distributed Block-diagonal Approximation Methods for Regularized Empirical Risk Minimization

Ching-pei Lee, Kai-Wei Chang

摘要:

近年来,越来越需要在大量数据上训练机器学习模型。因此,为经验风险最小化(ERM)设计高效的分布式优化算法已成为一个活跃且具有挑战性的研究课题。本文通过解决对偶问题,提出了一个灵活的分布式ERM训练框架,对现有的方法进行了统一的描述和比较。我们的方法只需要近似解的优化过程中涉及的子问题,是通用的,可应用于许多大规模的机器学习问题,包括分类,回归,结构化预测。我们表明,我们的方法享有更广泛的一类问题的全局线性收敛,并实现更快的经验性能,与现有的作品相比。

英文摘要:

In recent years, there is a growing need to train machine learning models on a huge volume of data. Designing efficient distributed optimization algorithms for empirical risk minimization (ERM) has therefore become an active and challenging research topic. In this paper, we propose a flexible framework for distributed ERM training through solving the dual problem, which provides a unified description and comparison of existing methods. Our approach requires only approximate solutions of the sub-problems involved in the optimization process, and is versatile to be applied on many large-scale machine learning problems including classification, regression, and structured prediction. We show that our approach enjoys global linear convergence for a broader class of problems, and achieves faster empirical performance, compared with existing works.

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。

↑