Non-Convex Bilevel Games with Critical Point Selection Maps

Michael Arbel (1) , Julien Mairal (1)

1 Thoth - Apprentissage de modèles à partir de données massives

Bilevel optimization problems involve two nested objectives, where an upper-level objective depends on a solution to a lower-level problem. When the latter is nonconvex, multiple critical points may be present, leading to an ambiguous definition of the problem. In this paper, we introduce a key ingredient for resolving this ambiguity through the concept of a selection map which allows one to choose a particular solution to the lower-level problem. Using such maps, we define a class of hierarchical games between two agents that resolve the ambiguity in bilevel problems. This new class of games requires introducing new analytical tools in Morse theory to extend implicit differentiation, a technique used in bilevel optimization resulting from the implicit function theorem. In particular, we establish the validity of such a method even when the latter theorem is inapplicable due to degenerate critical points. Finally, we show that algorithms for solving bilevel problems based on unrolled optimization solve these games up to approximation errors due to finite computational power. A simple correction to these algorithms is then proposed for removing these errors.

Domaines: Optimisation et contrôle [math.OC]

Michael Arbel, Julien Mairal. Non-Convex Bilevel Games with Critical Point Selection Maps. NeurIPS 2022 - 36th Conference on Neural Information Processing Systems, Nov 2022, New Orleans, United States. pp.1-34, ⟨10.48550/arXiv.2207.04888⟩. ⟨hal-03869097⟩