We consider the problem of sampling from a target distribution, which is \emph {not necessarily logconcave}, in the context of empirical risk minimization and stochastic optimization as presented in Raginsky et al. (2017). Non-asymptotic analysis results are established in the $L^1$-Wasserstein distance for the behaviour of Stochastic Gradient Langevin Dynamics (SGLD) algorithms. We allow the estimation of gradients to be performed even in the presence of \emph{dependent} data streams. Our convergence estimates are sharper and \emph{uniform} in the number of iterations, in contrast to those in previous studies.
翻译:在Raginsky等人(2017年)介绍的经验风险最小化和随机优化背景下,我们考虑从目标分布(不一定是对数值的对数值)取样的问题,在Raginsky等人(2017年)介绍的实验风险最小化和随机优化背景下,用1美元至Wasserstein的距离确定了非无损分析结果,用于Stochastic Gradient Langevin Directives(SGLD)算法的行为。我们允许即使在存在\emph{依赖}数据流的情况下也进行梯度估计。我们的趋同估计值在迭代数中是锐利的,与以前研究中的数字不同。