On Penalty-based Bilevel Gradient Descent Method

Author name not available (Why is that?)

Publication date: 10 February 2023

Abstract: Bilevel optimization enjoys a wide range of applications in hyper-parameter optimization, meta-learning and reinforcement learning. However, bilevel optimization problems are difficult to solve. Recent progress on scalable bilevel algorithms mainly focuses on bilevel optimization problems where the lower-level objective is either strongly convex or unconstrained. In this work, we tackle the bilevel problem through the lens of the penalty method. We show that under certain conditions, the penalty reformulation recovers the solutions of the original bilevel problem. Further, we propose the penalty-based bilevel gradient descent (PBGD) algorithm and establish its finite-time convergence for the constrained bilevel problem without lower-level strong convexity. Experiments showcase the efficiency of the proposed PBGD algorithm.

Has companion code repository: https://github.com/hanshen95/penalized-bilevel-gradient-descent

This page was built for publication: On Penalty-based Bilevel Gradient Descent Method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6426038)