采用小批量采样的随机近似EM算法的性质
Properties of the Stochastic Approximation EM Algorithm with Mini-batch Sampling
AI总结：
本文提出适用于潜变量模型的小批量采样随机近似EM算法，证明其在指数族模型下的收敛性，验证了小批量可加快收敛速度，并分析了批量规模对极限分布的影响，给出计算时间受限场景下的应用方法。
摘要：
为处理超大规模数据集，本文提出了适用于一般潜变量模型的蒙特卡洛马尔可夫链随机近似期望最大化算法的小批量版本。对于指数族模型，本文证明了随着迭代次数增加，该算法在经典条件下具有收敛性。数值实验验证了该小批量算法在多种模型中的性能，尤其突出了小批量采样能显著加快算法生成的估计量序列的收敛速度。此外，本文还分析了小批量规模对极限分布的影响，最后说明了在计算时间受限的实际场景中，如何利用小批量采样提升结果表现。
英文摘要：
To deal with very large datasets a mini-batch version of the Monte Carlo Markov Chain Stochastic Approximation Expectation-Maximization algorithm for general latent variable models is proposed. For exponential models the algorithm is shown to be convergent under classicalconditions as the number of iterations increases. Numerical experiments illustrate the performance of the mini-batch algorithm in various models.In particular, we highlight that mini-batch sampling results in an important speed-up of the convergence of the sequence of estimators generated by the algorithm. Moreover, insights on the effect of the mini-batch size on the limit distribution are presented. Finally, we illustrate how to use mini-batch sampling in practice to improve results when a constraint on the computing time is given.
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。
