The task aims to infer objects'

However,inmanyreal-worldtasks,the learned function is intended to satisfy domain-specific constraints. We focus on monotonicity constraints, which are common and require that the function's output increases with increasing values of specific input features.

If different options were available to each group offour values, then more advantageous choices canbemade, asillustrated inFigure 1.

Importantly, E2 is bounded independently ofS.

Below, we proceed to describe our contributions in greater detail. Our framework builds upon the seminal work of Jordan et al. [1998], which introduced the celebrated