English

Multi-block Min-max Bilevel Optimization with Applications in Multi-task Deep AUC Maximization

Optimization and Control 2022-11-22 v3 Artificial Intelligence Machine Learning Machine Learning

Abstract

In this paper, we study multi-block min-max bilevel optimization problems, where the upper level is non-convex strongly-concave minimax objective and the lower level is a strongly convex objective, and there are multiple blocks of dual variables and lower level problems. Due to the intertwined multi-block min-max bilevel structure, the computational cost at each iteration could be prohibitively high, especially with a large number of blocks. To tackle this challenge, we present a single-loop randomized stochastic algorithm, which requires updates for only a constant number of blocks at each iteration. Under some mild assumptions on the problem, we establish its sample complexity of O(1/ϵ4)O(1/\epsilon^4) for finding an ϵ\epsilon-stationary point. This matches the optimal complexity for solving stochastic nonconvex optimization under a general unbiased stochastic oracle model. Moreover, we provide two applications of the proposed method in multi-task deep AUC (area under ROC curve) maximization and multi-task deep partial AUC maximization. Experimental results validate our theory and demonstrate the effectiveness of our method on problems with hundreds of tasks.

Keywords

Cite

@article{arxiv.2206.00260,
  title  = {Multi-block Min-max Bilevel Optimization with Applications in Multi-task Deep AUC Maximization},
  author = {Quanqi Hu and Yongjian Zhong and Tianbao Yang},
  journal= {arXiv preprint arXiv:2206.00260},
  year   = {2022}
}
R2 v1 2026-06-24T11:35:32.179Z