Functional Bilevel Optimization for Machine Learning

arXiv:2403.20233v1 Announce Type: cross
Abstract: In this paper, we introduce a new functional point of view on bilevel optimization problems for machine learning, where the inner objective is minimized over a function space. These types of problems are most often solved by using methods developed in the parametric setting, where the inner objective is strongly convex with respect to the parameters of the prediction function. The functional point of view does not rely on this assumption and notably allows using …

abstract arxiv cs.lg function functional machine machine learning optimization paper parametric space stat.ml type types view