Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems
Two new research papers introduce novel first-order methods for tackling complex bilevel optimization problems. One paper proposes a barrier-metric approach for linearly constrained bilevel optimization, using logarithmic barrier smoothing to achieve differentiability and developing barrier-aware schedules for improved stability. The second paper presents penalty-based methods for bilevel optimization with minimax and constrained lower-level problems, offering improved oracle complexity bounds for both deterministic and stochastic settings, and extending to convex constrained lower-level minimization via Lagrangian duality. AI
IMPACT Introduces new algorithmic approaches for optimization problems that may have downstream applications in training complex AI models.