论文标题
原始双重增量梯度方法，用于非滑动和凸优化问题
Primal-Dual Incremental Gradient Method for Nonsmooth and Convex Optimization Problems
论文作者
论文摘要
在本文中，我们考虑了与圆锥约束的非平滑凸有限-AM问题。为了克服投影到约束集并计算完整（子）梯度的挑战，我们引入了一个原始的双重增量梯度方案，其中仅使用一个组件函数和两个约束来以周期性的顺序更新每个原始的双重子题。我们在这种情况下，在次优和不可行的角度上证明了渐近的倾斜度收敛速率，这比最新的增量梯度方案有所改善。数值结果表明，所提出的方案与竞争方法很好地比较。
In this paper, we consider a nonsmooth convex finite-sum problem with a conic constraint. To overcome the challenge of projecting onto the constraint set and computing the full (sub)gradient, we introduce a primal-dual incremental gradient scheme where only a component function and two constraints are used to update each primal-dual sub-iteration in a cyclic order. We demonstrate an asymptotic sublinear rate of convergence in terms of suboptimality and infeasibility which is an improvement over the state-of-the-art incremental gradient schemes in this setting. Numerical results suggest that the proposed scheme compares well with competitive methods.
