Theoretical Smoothing Frameworks for Nonsmooth Simple Bilevel Problems

• 成果类型: Article; Early Access
• 署名作者: Alcantara, Jan Harold; Takeda, Akiko
• 署名单位: RIKEN; University of Tokyo
• 刊物名称: MATHEMATICS OF OPERATIONS RESEARCH
• ISSN/ISSBN: 0364-765X; 1526-5471
• DOI: 10.1287/moor.2024.0405
• 发表日期: 2026-03-24
• 关键词: bilevel optimization; value function; smooth approximation; gradient consistency; quadratic regularization; Entropic Regularization; MIN-MAX PROBLEMS

摘要

Bilevel programming has recently received a great deal of attention because of its abundant applications in many areas. We study a class of bilevel problems in which the lower-level feasible set is independent of the upper-level variables. The optimal value function approach provides a useful reformulation of the bilevel problem, but its utility is often limited because of the nonsmoothness of the value function even in cases when the associated lower-level function is smooth. In this paper, we present two smoothing strategies for the value function associated with lower-level functions that are not necessarily smooth but are Lipschitz continuous. The first method employs quadratic regularization for partially convex lower-level functions, whereas the second utilizes entropic regularization for general lower-level objective functions. Meanwhile, the property known as gradient consistency is crucial in ensuring that a designed smoothing algorithm is globally subsequentially convergent to stationary points of the value function reformulation. With this motivation, we prove that the proposed smooth approximations satisfy the gradient consistent property under certain conditions on the lower-level function.