The Missing Indicator Method: From Low to High Dimensions

1 code implementation • 16 Nov 2022 • Mike Van Ness, Tomas M. Bosschieter, Roberto Halpin-Gregorio, Madeleine Udell

In this paper, we show empirically and theoretically that MIM improves performance for informative missing values, and we prove that MIM does not hurt linear models asymptotically for uninformative missing values.

Imputation Vocal Bursts Intensity Prediction