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 1609.02191cs.ITcond-mat.dis-nnmath.IT
收藏

高维稀疏PCA的在线学习:精确动力学和相变

Online Learning for Sparse PCA in High Dimensions: Exact Dynamics and Phase Transitions

Chuang Wang, Yue M. Lu

摘要:

我们研究动态的在线算法学习稀疏领先的特征向量从尖峰协方差模型产生的样本。该算法结合了经典的Oja在线PCA方法,在每次迭代时采用元素非线性来提高稀疏性。在高维极限,联合经验措施的基本稀疏特征向量和它的估计算法所提供的弱收敛到一个确定性的,测量值的过程。这个比例限制的特点是作为一个非线性偏微分方程的唯一解决方案,它提供了准确的信息,关于算法的渐近性能。例如,稀疏支持恢复中的余弦相似度和误分类率等性能指标可以通过检查限制动态来获得。非线性偏微分方程的稳态分析也揭示了一个有趣的相变现象。虽然我们的分析是渐进的性质,数值模拟表明,理论预测是准确的中等信号尺寸。

英文摘要:

We study the dynamics of an online algorithm for learning a sparse leading eigenvector from samples generated from a spiked covariance model. This algorithm combines the classical Oja's method for online PCA with an element-wise nonlinearity at each iteration to promote sparsity. In the high-dimensional limit, the joint empirical measure of the underlying sparse eigenvector and its estimate provided by the algorithm is shown to converge weakly to a deterministic, measure-valued process. This scaling limit is characterized as the unique solution of a nonlinear PDE, and it provides exact information regarding the asymptotic performance of the algorithm. For example, performance metrics such as the cosine similarity and the misclassification rate in sparse support recovery can be obtained by examining the limiting dynamics. A steady-state analysis of the nonlinear PDE also reveals an interesting phase transition phenomenon. Although our analysis is asymptotic in nature, numerical simulations show that the theoretical predictions are accurate for moderate signal dimensions.

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。

↑