Review for NeurIPS paper: Coresets for Regressions with Panel Data

Summary and Contributions: The paper deals with coresets (data summary obtained by subsampling and approximating the objective function for all queries) for least squares regression on panel data. In the usual "cross-sectional" setting the data consists of N individuals with d features each. Panel data extends this by introducing a time-series for each individual, consisting of the d features measured at T time steps. Moreover a correlation structure is introduced between the time steps to model dependencies over the time axes. The objective is to minimize the sum over all individuals of the least squares regressions subject to correlations between the time steps. The variables are thus the regression parameters as well as the defining parameters of the covariance structure.