论文标题
Tseng型自随机前回向算法，用于单调夹杂物
A Tseng type stochastic forward-backward algorithm for monotone inclusions
论文作者
论文摘要
在本文中，我们提出了经典Tseng的前回答方法的随机版本，该方法具有惯性术语，用于求解由最大单调算子和真实希尔伯特空间中的单值单调算子的总和给出的单调夹杂物。我们获得了一般情况的几乎确定的收敛性，并在强元单调案例中预期的是$ \ MATHCAL {O}（1/N）$。 此外，我们得出了$ \ Mathcal {O}（1/N）$对于鞍点问题的原始二次间隙的速率收敛。
In this paper, we propose a stochastic version of the classical Tseng's forward-backward-forward method with inertial term for solving monotone inclusions given by the sum of a maximal monotone operator and a single-valued monotone operator in real Hilbert spaces. We obtain the almost sure convergence for the general case and the rate $\mathcal{O}(1/n)$ in expectation for the strong monotone case. Furthermore, we derive $\mathcal{O}(1/n)$ rate convergence of the primal-dual gap for saddle point problems.
