arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1710.07926math.STstat.TH
收藏

关于离散化平均随机梯度算法的收敛速度

On the rates of convergence of Parallelized Averaged Stochastic Gradient Algorithms

Antoine Godichon-Baggioni, Sofiane Saadane

摘要:

在过去的十年中,对高维和函数数据分析的兴趣日益增长,导致了一项重要的研究,从而开发了大量的技术。例如,将数据分布和处理到不同机器中的并行化算法是处理高维空间中的大样本值的一个很好的答案。我们在这里介绍了一个并行化的平均随机梯度算法,它可以有效地和递归地处理数据,因此,不需要考虑数据到机器的分布是否均匀。对于强凸和局部强凸目标,给出了并行化估计的二次平均收敛速率和渐近正态性。

英文摘要:

The growing interest for high dimensional and functional data analysis led in the last decade to an important research developing a consequent amount of techniques. Parallelized algorithms, which consist in distributing and treat the data into different machines, for example, are a good answer to deal with large samples taking values in high dimensional spaces. We introduce here a parallelized averaged stochastic gradient algorithm, which enables to treat efficiently and recursively the data, and so, without taking care if the distribution of the data into the machines is uniform. The rate of convergence in quadratic mean as well as the asymptotic normality of the parallelized estimates are given, for strongly and locally strongly convex objectives.

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。

↑