Streaming Heteroscedastic Probabilistic PCA with Missing Data

Streaming principal component analysis (PCA) is an integral tool in large-scale machine learning for rapidly estimating low-dimensional subspaces from very high-dimensional data arriving at a high rate. However, modern datasets increasingly combine data from a variety of sources, and thus may exhibit heterogeneous quality across samples. Standard streaming PCA algorithms do not account for non-uniform noise, so their subspace estimates can quickly degrade. While the recently proposed Heteroscedastic Probabilistic PCA Technique (HePPCAT) addresses this heterogeneity, it was not designed to handle streaming data, which may exhibit non-stationary behavior. Moreover, HePPCAT does not allow for missing entries in the data, which can be common in streaming data. This paper proposes the Streaming HeteroscedASTic Algorithm for PCA (SHASTA-PCA) to bridge this divide. SHASTA-PCA employs a stochastic alternating expectation maximization approach that jointly learns the low-rank latent factors and the unknown noise variances from streaming data that may have missing entries and heteroscedastic noise, all while maintaining a low memory and computational footprint. Numerical experiments demonstrate the superior subspace estimation of our method compared to state-of-the-art streaming PCA algorithms in the heteroscedastic setting. Finally, we illustrate SHASTA-PCA applied to highly heterogeneous real data from astronomy.