Scalable Second-order Riemannian Optimization for $K$-means Clustering
可扩展的二次黎曼优化用于K均值聚类
机构 * Department of Statistics, University of Illinois Urbana-Champaign(统计系,伊利诺伊大学厄巴纳-香槟分校) ; Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign(电气与计算机工程系,伊利诺伊大学厄巴纳-香槟分校) ; Department of Mathematics, University of Southern California(数学系,南加州大学)
AI总结 本文提出了一种基于二次黎曼优化的K均值聚类方法,通过分解流形结构实现线性时间复杂度,显著提升收敛速度并保持统计准确性。
Journal ref The Fourteenth International Conference on Learning Representations (ICLR), 2026