arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.14977stat.MLmath.OCmath.STstat.MEstat.TH
收藏

子空间约束均值漂移算法的线性收敛性:从欧氏数据到方向数据

Linear Convergence of the Subspace Constrained Mean Shift Algorithm: From Euclidean to Directional Data

Yikun Zhang, Yen-Chi Chen

AI总结:

本文证明了子空间约束均值漂移算法的线性收敛性,并将其推广到方向数据,建立了方向数据密度脊的稳定性定理。

摘要:

本文研究子空间约束均值漂移(SCMS)算法的线性收敛性,该算法是一种用于识别由核密度估计器定义的密度脊的著名算法。通过论证SCMS算法是具有自适应步长的子空间约束梯度上升(SCGA)算法的一种特殊变体,我们推导出此类SCGA算法的线性收敛性。虽然现有研究主要关注欧氏空间中的密度脊,我们将密度脊和SCMS算法推广到方向数据。特别地,我们建立了方向数据密度脊的稳定性定理,并证明了所提出的方向SCMS算法的线性收敛性。

英文摘要:

This paper studies the linear convergence of the subspace constrained mean shift (SCMS) algorithm, a well-known algorithm for identifying a density ridge defined by a kernel density estimator. By arguing that the SCMS algorithm is a special variant of a subspace constrained gradient ascent (SCGA) algorithm with an adaptive step size, we derive the linear convergence of such SCGA algorithm. While the existing research focuses mainly on density ridges in the Euclidean space, we generalize density ridges and the SCMS algorithm to directional data. In particular, we establish the stability theorem of density ridges with directional data and prove the linear convergence of our proposed directional SCMS algorithm.

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。

↑