用于马尔可夫数据的流式主成分分析（英文版）

英文标题：Streaming PCA for Markovian Data中文摘要：研究了数据点从无法分解的 Markov 链中采样的流式主成分分析（PCA）问题，提出了一个新的算法并证明了其收敛速率，解决了使用 MCMC 算法从链的稳态分布中采样的问题。英文摘要：Since its inception in Erikki Oja's seminal paper in 1982, Oja's algorithmhas become an established method for streaming principle component analysis(PCA). We study the problem of streaming PCA, where the data-points are sampledfrom an irreducible, aperiodic, and reversible Markov chain. Our goal is toestimate the top eigenvector of the unknown covariance matrix of