arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1604.00526math.OC
收藏

非光滑非凸问题的异步PALM算法

The Asynchronous PALM Algorithm for Nonsmooth Nonconvex Problems

Damek Davis

摘要:

我们介绍了异步PALM算法,一个新的扩展的近似交替线性最小化(PALM)算法解决非光滑,非凸最优化问题。与PALM算法一样,异步PALM算法的每一步都会更新一个坐标块;但与PALM算法不同的是,异步PALM算法不需要一个接一个地进行顺序更新。相反,我们的新算法允许每个坐标块以任何顺序异步更新,这意味着任何数量的计算核心都可以并行计算更新,而无需同步计算。在实践中,这种并行化策略通常会导致加速比随着计算核心的数量线性增加。我们介绍了两个变种的异步PALM算法,一个随机和一个确定性。在随机\textit{and}确定的情况下,我们证明了算法的聚类点是平稳点。在确定性的情况下,我们表明,该算法的全局收敛时,Kurdyka-Eschojasiewicz属性保持密切相关的目标函数的功能,我们推导出它的收敛速度在一个共同的特殊情况。最后,我们提供了一个具体的情况下,我们的假设成立。

英文摘要:

We introduce the Asynchronous PALM algorithm, a new extension of the Proximal Alternating Linearized Minimization (PALM) algorithm for solving nonsmooth, nonconvex optimization problems. Like the PALM algorithm, each step of the Asynchronous PALM algorithm updates a single block of coordinates; but unlike the PALM algorithm, the Asynchronous PALM algorithm eliminates the need for sequential updates that occur one after the other. Instead, our new algorithm allows each of the coordinate blocks to be updated asynchronously and in any order, which means that any number of computing cores can compute updates in parallel without synchronizing their computations. In practice, this asynchronization strategy often leads to speedups that increase linearly with the number of computing cores. We introduce two variants of the Asynchronous PALM algorithm, one stochastic and one deterministic. In the stochastic \textit{and} deterministic cases, we show that cluster points of the algorithm are stationary points. In the deterministic case, we show that the algorithm converges globally whenever the Kurdyka-Łojasiewicz property holds for a function closely related to the objective function, and we derive its convergence rate in a common special case. Finally, we provide a concrete case in which our assumptions hold.

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。

↑