arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.06528math.OCcs.LGstat.ML
收藏

原始-对偶坐标下降的随机外推

Random extrapolation for primal-dual coordinate descent

EPFL(洛桑联邦理工学院);Télécom Paris(巴黎电信学院);Institut Polytechnique de Paris(巴黎综合理工学院)

Ahmet Alacaoglu, Olivier Fercoq, Volkan Cevher

摘要:

我们引入了一种随机外推的原始-对偶坐标下降法,该方法适应于数据矩阵的稀疏性和目标函数的有利结构。我们的方法只更新原始和对偶变量的一个子集与稀疏的数据,它使用大的步长与密集的数据,保留的好处,为每种情况下设计的具体方法。除了适应稀疏性,我们的方法达到快速收敛的保证在有利的情况下\textit{without any modifications}。特别地,我们证明了度量次正则下的线性收敛性,它适用于强凸-强凹问题和分段线性二次函数。在一般的凸-凹情形下,我们证明了序列的几乎必然收敛和原始-对偶间隙和目标值的最佳次线性收敛速度。数值证据证明了我们的方法在稀疏和密集环境中的最先进的经验性能,匹配和改进了现有的方法。

英文摘要:

We introduce a randomly extrapolated primal-dual coordinate descent method that adapts to sparsity of the data matrix and the favorable structures of the objective function. Our method updates only a subset of primal and dual variables with sparse data, and it uses large step sizes with dense data, retaining the benefits of the specific methods designed for each case. In addition to adapting to sparsity, our method attains fast convergence guarantees in favorable cases \textit{without any modifications}. In particular, we prove linear convergence under metric subregularity, which applies to strongly convex-strongly concave problems and piecewise linear quadratic functions. We show almost sure convergence of the sequence and optimal sublinear convergence rates for the primal-dual gap and objective values, in the general convex-concave case. Numerical evidence demonstrates the state-of-the-art empirical performance of our method in sparse and dense settings, matching and improving the existing methods.

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。

↑