Multicalibrated Regression for Downstream Fairness
share
We show how to take a regression function f̂ that is appropriately “multicalibrated” and efficiently post-process it into an approximately error minimizing classifier satisfying a large variety of fairness constraints. The post-processing requires no labeled data, and only a modest amount of unlabeled data and computation. The computational and sample complexity requirements of computing f̂ are comparable to the requirements for solving a single fair learning task optimally, but it can in fact be used to solve many different downstream fairness-constrained learning problems efficiently. Our post-processing method easily handles intersecting groups, generalizing prior work on post-processing regression functions to satisfy fairness constraints that only applied to disjoint groups. Our work extends recent work showing that multicalibrated regression functions are “omnipredictors” (i.e. can be post-processed to optimally solve unconstrained ERM problems) to constrained optimization.
READ FULL TEXT
