arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2305.02456math.STcs.LGstat.MLstat.TH
收藏

马尔可夫数据的流式主成分分析

Streaming PCA for Markovian Data

University of Texas at Austin(德克萨斯大学奥斯汀分校)

Syamantak Kumar, Purnamrita Sarkar

AI总结:

针对马尔可夫链采样的流式PCA,本文提出Oja算法在全量数据上的首个尖锐收敛速率,消除了下采样导致的对样本量的对数依赖。

摘要:

自1982年问世以来,Oja算法已成为流式主成分分析(PCA)的成熟方法。我们研究流式PCA问题,其中数据点采自一个不可约、非周期且可逆的马尔可夫链。我们的目标是估计平稳分布未知协方差矩阵的主特征向量。该设定适用于数据仅能通过马尔可夫链蒙特卡洛(MCMC)类算法采样,且目标是对平稳分布参数进行推断的场景。文献中Oja算法的大多数收敛保证假设数据点是独立同分布(IID)采样的。对于具有马尔可夫依赖的数据流,通常会对数据进行下采样以获得“近似”独立的数据流。在本文中,我们获得了Oja算法在全量数据上的首个尖锐收敛速率,其中我们消除了因下采样策略丢弃数据而产生的对样本量$n$的对数依赖。

英文摘要:

Since its inception in 1982, Oja's algorithm has become an established method for streaming principle component analysis (PCA). We study the problem of streaming PCA, where the data-points are sampled from an irreducible, aperiodic, and reversible Markov chain. Our goal is to estimate the top eigenvector of the unknown covariance matrix of the stationary distribution. This setting has implications in scenarios where data can solely be sampled from a Markov Chain Monte Carlo (MCMC) type algorithm, and the objective is to perform inference on parameters of the stationary distribution. Most convergence guarantees for Oja's algorithm in the literature assume that the data-points are sampled IID. For data streams with Markovian dependence, one typically downsamples the data to get a "nearly" independent data stream. In this paper, we obtain the first sharp rate for Oja's algorithm on the entire data, where we remove the logarithmic dependence on the sample size, $n$, resulting from throwing data away in downsampling strategies.

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。

↑