论文标题
GEOM-SPIDER-EM：更快的方差降低了非凸有限和优化的随机期望最大化
Geom-SPIDER-EM: Faster Variance Reduced Stochastic Expectation Maximization for Nonconvex Finite-Sum Optimization
论文作者
论文摘要
期望最大化（EM）算法是潜在变量模型中推断的关键参考。不幸的是，在大规模学习环境中，其计算成本是高度启发的。在本文中，我们提出了随机路径综合估计量EM（蜘蛛网）的扩展，并为这种新型算法得出复杂性界限，该算法旨在解决平滑的非凸有限的有限量和优化问题。我们表明，它达到了与蜘蛛网相同的艺术复杂性界限。并提供线性收敛速率的条件。数值结果支持我们的发现。
The Expectation Maximization (EM) algorithm is a key reference for inference in latent variable models; unfortunately, its computational cost is prohibitive in the large scale learning setting. In this paper, we propose an extension of the Stochastic Path-Integrated Differential EstimatoR EM (SPIDER-EM) and derive complexity bounds for this novel algorithm, designed to solve smooth nonconvex finite-sum optimization problems. We show that it reaches the same state of the art complexity bounds as SPIDER-EM; and provide conditions for a linear rate of convergence. Numerical results support our findings.
