Subspace Tracking from Missing and Outlier Corrupted Data

We study the related problems of subspace tracking in the presence of missing data (ST-miss) as well as robust subspace tracking with missing data (RST-miss). Here "robust" refers to robustness to sparse outliers. In recent work, we have studied the RST problem without missing data. In this work, we show that simple modifications of our solution approach for RST also provably solve ST-miss and RST-miss under weaker and similar assumptions respectively. To our knowledge, our result is the first complete guarantee for both ST-miss and RST-miss. This means we are able to show that, under assumptions on only the algorithm inputs (input data and/or initialization), the output subspace estimates are close to the true data subspaces at all times. Our guarantees hold under mild and easily interpretable assumptions and handle time-varying subspaces (unlike all previous work). We also show that our algorithm and its extensions are fast and have competitive experimental performance when compared with existing methods.