Optimal Semi-supervised Subsampling via Predictive Inference

In big data era, subsampling or sub-data selection techniques are often adopted to extract a fraction of informative individuals from the massive data. Existing subsampling algorithms focus mainly on obtaining a representative subset to achieve best estimation accuracy under a given class of models. In this talk, we consider a semi-supervised setting wherein a small or moderate sized “labeled” data is available in addition to a much larger sized “unlabeled” data. The goal is to sample from the unlabeled data with a give budget to obtain informative individuals that are characterized by their unobserved responses. I will introduce an optimal subsampling procedure that is able to maximize the diversity of the selected subsample and control false selection rate (FSR) simultaneously, allowing us to explore reliable information as much as possible.