Bilevel and Min-Max Optimization

Theory and algorithms for bilevel and minimax optimization problems

Bilevel optimization and min-max optimization problems arise in many important applications including hyperparameter tuning, adversarial machine learning, robust optimization, and game theory. These problems are notoriously difficult due to their nested structure and nonconvex-nonconcave nature.

Our group develops novel algorithms and theoretical frameworks for solving these challenging problems, with applications in machine learning, signal processing, and communications.

Selected Publications

  • Songtao Lu, Ioannis Tsaknakis, Mingyi Hong and Yongxin Chen, “Block Alternating Optimization for Non-Convex Min-Max Problems: Algorithms and Applications in Signal Processing and Communications”, IEEE Transactions on Signal Processing, Dec. 2019
  • Meisam Razaviyayn, T. Huang, S. Lu, M. Nouiehed, M. Sanjabi, M. Hong, “Non-convex Min-Max Optimization: Applications, Challenges, and Recent Theoretical Advances”, IEEE Signal Processing Magazine, 2020