B1235
Title: A sequential experimental design approach for sub-setting big data
Authors: Christopher Drovandi - Queensland University of Technology (Australia) [presenting]
Abstract: Big Datasets are endemic but are often notoriously difficult to analyze because of their size, heterogeneity and quality. A sequential optimal experimental design approach is developed to obtain an informative subsample from the large dataset for the model of interest. The approach is shown as superior to random subsampling through several examples.