arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.09587math.OCcs.MA
收藏

全局Optimization的分布式随机梯度算法

On Distributed Stochastic Gradient Algorithms for Global Optimization

Brian Swenson, Anirudh Sridhar, H. Vincent Poor

摘要:

研究了光滑非凸最优化问题全局极小点的网络计算问题。众所周知,分布式梯度下降型算法可以通过添加缓慢衰减的高斯噪声以逃避局部极小值来实现收敛到全局极小值的集合。然而,据以确定会出现趋同的技术假设在实践中可能具有限制性。特别是,在已知的收敛结果中,代理所拥有的局部目标函数需要满足高度限制性的有界梯度相异度条件。本文证明了收敛到全局极小值集,同时放松这一关键假设。

英文摘要:

The paper considers the problem of network-based computation of global minima in smooth nonconvex optimization problems. It is known that distributed gradient-descent-type algorithms can achieve convergence to the set of global minima by adding slowly decaying Gaussian noise in order escape local minima. However, the technical assumptions under which convergence is known to occur can be restrictive in practice. In particular, in known convergence results, the local objective functions possessed by agents are required to satisfy a highly restrictive bounded-gradient-dissimilarity condition. The paper demonstrates convergence to the set of global minima while relaxing this key assumption.

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。

↑