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 1409.6086stat.MLmath.OC
收藏

并行分布式块坐标Frank-Wolfe算法

Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms

Yu-Xiang Wang, Veeranjaneyulu Sadhanala, Wei Dai, Willie Neiswanger, Suvrit Sra, Eric P. Xing

摘要:

我们开发并行和分布式的弗兰克-沃尔夫算法,前者在共享内存的机器上的迷你,后者在延迟更新框架。只要有可能,我们就异步执行计算,这有助于在多核机器和分布式环境中实现加速。此外,而不是最坏情况下的有界延迟,我们的方法只依赖于(轻度)\emph{expected}延迟,使他们能够强大的掉队者和故障工作线程。我们的算法假设了块可分的约束条件,并继承了最近的块坐标Frank-Wolfe(BCFW)方法\citep{lacoste2013block}。我们的分析揭示了问题相关的数量,我们的方法在BCFW的加速。我们目前的实验结构SVM和组融合套索,获得显着的加速比竞争国家的最先进的(和同步)的方法。

英文摘要:

We develop parallel and distributed Frank-Wolfe algorithms; the former on shared memory machines with mini-batching, and the latter in a delayed update framework. Whenever possible, we perform computations asynchronously, which helps attain speedups on multicore machines as well as in distributed environments. Moreover, instead of worst-case bounded delays, our methods only depend (mildly) on \emph{expected} delays, allowing them to be robust to stragglers and faulty worker threads. Our algorithms assume block-separable constraints, and subsume the recent Block-Coordinate Frank-Wolfe (BCFW) method~\citep{lacoste2013block}. Our analysis reveals problem-dependent quantities that govern the speedups of our methods over BCFW. We present experiments on structural SVM and Group Fused Lasso, obtaining significant speedups over competing state-of-the-art (and synchronous) 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。

↑