arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1608.02010cs.LG
收藏

通信有效的核机器并行块最小化

Communication-Efficient Parallel Block Minimization for Kernel Machines

University of California, Davis(加州大学戴维斯分校);University of Texas, Austin(德克萨斯大学奥斯汀分校)

Cho-Jui Hsieh, Si Si, Inderjit S. Dhillon

摘要:

核机器通常在各种任务上产生卓越的预测性能;然而,它们遭受严重的计算挑战。在本文中,我们展示了如何克服加速内核机器的重要挑战。特别是,我们开发了一个并行块最小化框架,用于解决核机器,包括核SVM和核逻辑回归。我们的框架通过形成Hessian矩阵的块对角近似来将问题划分为更小的子问题。然后近似并行地求解子问题。在此之后,通信有效的线搜索过程中开发,以确保在每次迭代的目标函数值的充分减少。我们证明了所提出的方法的全局线性收敛速度与广泛的一类子问题求解器,我们的分析涵盖强凸和一些非强凸函数。我们应用我们的算法来解决分布式系统上的大规模核SVM问题,并显示出显着的改善现有的并行求解器。例如,在具有50万个样本的covtype数据集上,我们的算法可以使用32台机器在20秒内获得96%准确度的近似解,而所有其他并行核SVM求解器需要超过2000秒才能获得95%准确度的解。此外,我们的算法可以扩展到非常大的数据集,例如具有800万个样本和2000万个特征的kdd代数数据集。

英文摘要:

Kernel machines often yield superior predictive performance on various tasks; however, they suffer from severe computational challenges. In this paper, we show how to overcome the important challenge of speeding up kernel machines. In particular, we develop a parallel block minimization framework for solving kernel machines, including kernel SVM and kernel logistic regression. Our framework proceeds by dividing the problem into smaller subproblems by forming a block-diagonal approximation of the Hessian matrix. The subproblems are then solved approximately in parallel. After that, a communication efficient line search procedure is developed to ensure sufficient reduction of the objective function value at each iteration. We prove global linear convergence rate of the proposed method with a wide class of subproblem solvers, and our analysis covers strongly convex and some non-strongly convex functions. We apply our algorithm to solve large-scale kernel SVM problems on distributed systems, and show a significant improvement over existing parallel solvers. As an example, on the covtype dataset with half-a-million samples, our algorithm can obtain an approximate solution with 96% accuracy in 20 seconds using 32 machines, while all the other parallel kernel SVM solvers require more than 2000 seconds to achieve a solution with 95% accuracy. Moreover, our algorithm can scale to very large data sets, such as the kdd algebra dataset with 8 million samples and 20 million features.

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。

↑