Near-Optimal Solutions of Constrained Learning Problems

arXiv:2403.11844v1 Announce Type: new
Abstract: With the widespread adoption of machine learning systems, the need to curtail their behavior has become increasingly apparent. This is evidenced by recent advancements towards developing models that satisfy robustness, safety, and fairness requirements. These requirements can be imposed (with generalization guarantees) by formulating constrained learning problems that can then be tackled by dual ascent algorithms. Yet, though these algorithms converge in objective value, even in non-convex settings, they cannot guarantee that their outcome is …

abstract adoption arxiv become behavior cs.lg eess.sp fairness learning systems machine machine learning math.oc near requirements robustness safety solutions systems type