混合模型中PCA连通性分析的精确符号恢复
Exact Sign Recovery for PCA Connectivity Analysis in Mixture Models
浏览论文内容
中文总结 AI 辅助
本文研究PCA连通性分析中的精确符号恢复，提出充分条件并给出渐近精确截止值，无需条件数有界。
中文摘要 AI 辅助
我们研究了基于前K-1个主成分的Ding和He（2004）PCA连通性构建的精确符号恢复问题。对于任意固定数量的具有仿射独立均值的分量，我们显式地推导了预言信号投影。在各向异性次高斯噪声和随机分量大小下，行向特征空间界给出了一个充分条件，该条件由最弱信号方向控制，用于恢复所有连通性符号，而不需要非零信号谱的条件数有界。在各向同性高斯噪声和固定均值形状下，我们获得了渐近精确的截止值，当混合比例相等且均值构成正单纯形时，该截止值具有显式公式。
英文摘要
We study exact sign recovery for the PCA connectivity construction of Ding and He (2004), based on the first K-1 principal components. For any fixed number of components with affinely independent means, we derive the oracle signal projection explicitly. Under anisotropic sub-Gaussian noise and random component sizes, a rowwise eigenspace bound yields a sufficient condition, governed by the weakest signal direction, for recovering all connectivity signs without requiring a bounded condition number of the nonzero signal spectrum. Under isotropic Gaussian noise with a fixed mean shape, we obtain an asymptotically sharp cutoff, with an explicit formula when the mixing proportions are equal and the means form a regular simplex.
发表机构
- Joint Graduate School of Mathematics for Innovation, Kyushu University（九州大学数学创新联合研究生院）
机构由 AI 辅助整理，请以论文原文为准。
