Sample splitting is one of the most tried-and-true tools in the data scientist toolbox. A recent paper (Neufeld, et al. 2023) provided a remarkable alternative, which the authors showed to be attractive in situations where sample splitting is not possible. In this talk, we will show that sufficiency is the key underlying principle that makes their approach possible, and based on this observation we introduce a generalization that greatly widens the scope of applicability.
Speaker: Jacob Bien, PhD, Associate Professor of Data Sciences and Operations, Marshall School of Business, Univ. of Southern California
To obtain Zoom link please email: Liz Buggs