Enhanced Bilevel Optimization via Bregman Distance. (arXiv:2107.12301v2 [math.OC] UPDATED)

Bilevel optimization has been widely applied to many machine learning
problems such as hyperparameter optimization, policy optimization and meta
learning. Although many bilevel optimization methods recently have been
proposed to solve the bilevel optimization problems, they still suffer from
high computational complexities and do not consider the more general bilevel
problems with nonsmooth regularization. In the paper, thus, we propose a class
of enhanced bilevel optimization methods by using Bregman distance to solve
bilevel optimization problems, where the outer subproblem …

arxiv math optimization