arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1610.07487math.STstat.MLstat.TH
收藏

核学习中的谱算法的简化

Parallelizing Spectral Algorithms for Kernel Learning

Gilles Blanchard, Nicole Mücke

摘要:

我们考虑一个分布式学习方法在监督学习的一大类谱正则化方法在RKHS框架。大小为n的数据集被划分为$m=O(n^α)$不相交的子集。在每个子集上,应用一些谱正则化方法(属于大类,特别包括核岭回归、$L^2$ -提升和谱截止)。回归函数$f$然后通过简单的平均来估计,导致计算时间的大幅减少。我们发现,如果m增长足够慢(对应于$α$的上界)作为$n \to \infty$,根据$f$和内在维数的平滑假设,极大极小最优收敛率被保留。在精神上,我们的方法是经典的。

英文摘要:

We consider a distributed learning approach in supervised learning for a large class of spectral regularization methods in an RKHS framework. The data set of size n is partitioned into $m=O(n^α)$ disjoint subsets. On each subset, some spectral regularization method (belonging to a large class, including in particular Kernel Ridge Regression, $L^2$-boosting and spectral cut-off) is applied. The regression function $f$ is then estimated via simple averaging, leading to a substantial reduction in computation time. We show that minimax optimal rates of convergence are preserved if m grows sufficiently slowly (corresponding to an upper bound for $α$) as $n \to \infty$, depending on the smoothness assumptions on $f$ and the intrinsic dimensionality. In spirit, our approach is classical.

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。

↑