首页> 外文期刊>IEEE Transactions on Information Theory >A Theoretical Analysis of Noisy Sparse Subspace Clustering on Dimensionality-Reduced Data
【24h】

A Theoretical Analysis of Noisy Sparse Subspace Clustering on Dimensionality-Reduced Data

机译:降维数据的噪声稀疏子空间聚类的理论分析

获取原文
获取原文并翻译 | 示例
           

摘要

Subspace clustering is the problem of partitioning unlabeled data points into a number of clusters so that data points within one cluster lie approximately on a low-dimensional linear subspace. In many practical scenarios, the dimensionality of data points to be clustered is compressed due to the constraints of measurement, computation, or privacy. In this paper, we study the theoretical properties of a popular subspace clustering algorithm named sparse subspace clustering (SSC) and establish formal success conditions of SSC on dimensionality-reduced data. Our analysis applies to the most general fully deterministic model, where both underlying subspaces and data points within each subspace are deterministically positioned, and also a wide range of dimensionality reduction techniques (e.g., Gaussian random projection, uniform subsampling, and sketching) that fall into a subspace embedding framework. Finally, we apply our analysis to a differentially private SSC algorithm and established both privacy and utility guarantees of the proposed method.
机译:子空间聚类是将未标记的数据点划分为多个簇的问题,因此一个簇内的数据点大约位于低维线性子空间上。在许多实际情况下,由于测量,计算或保密性的限制,要聚类的数据点的维数被压缩。在本文中,我们研究了一种流行的子空间聚类算法-稀疏子空间聚类(SSC)的理论性质,并为降维数据建立了SSC的形式化成功条件。我们的分析适用于最通用的完全确定性模型,其中确定性地定位了基础子空间和每个子空间中的数据点,并且还涉及了各种各样的降维技术(例如,高斯随机投影,均匀子采样和草绘)子空间嵌入框架。最后,我们将分析应用于差分私有SSC算法,并建立了所提出方法的隐私和效用保证。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号