Timezone: »

 
Poster
Consistent Estimators for Learning to Defer to an Expert
Hussein Mozannar · David Sontag

Wed Jul 15 05:00 AM -- 05:45 AM & Wed Jul 15 04:00 PM -- 04:45 PM (PDT) @ Virtual #None

Learning algorithms are often used in conjunction with expert decision makers in practical scenarios, however this fact is largely ignored when designing these algorithms. In this paper we explore how to learn predictors that can either predict or choose to defer the decision to a downstream expert. Given only samples of the expert's decisions, we give a procedure based on learning a classifier and a rejector and analyze it theoretically. Our approach is based on a novel reduction to cost sensitive learning where we give a consistent surrogate loss for cost sensitive learning that generalizes the cross entropy loss. We show the effectiveness of our approach on a variety of experimental tasks.

Author Information

Hussein Mozannar (Massachusetts Institute of Technology)
David Sontag (Massachusetts Institute of Technology)

More from the Same Authors