The geometry of losses

Abstract

Loss functions are central to machine learning because they are the means by which the quality of a prediction is evaluated. Any loss that is not proper, or can not be transformed to be proper via a link function is inadmissible. All admissible losses for n-class problems can be obtained in terms of a convex body in ℝn. We show this explicitly and show how some existing results simplify when viewed from this perspective. This allows the development of a rich algebra of losses induced by binary operations on convex bodies (that return a convex body). Furthermore it allows us to define an "inverse loss" which provides a universal "substitution function" for the Aggregating Algorithm. In doing so we show a formal connection between proper losses and norms.