报告题目：A Provably Convergent Plug-and-Play Framework for Stochastic Bilevel Optimization

报告人：张进教授（南方科技大学）

报告时间：2026年9月7日（周一）下午4：30-5：30

报告地点：数博彩平台425报告厅

报告摘要：Bilevel optimization has recently attracted significant attention in machine learning due to its wide range of applications and advanced hierarchical optimization capabilities. In this paper, we propose a plug-and-play framework, named PnPBO, for developing and analyzing stochastic bilevel optimization methods. This framework integrates both modern unbiased and biased stochastic estimators into the single-loop bilevel optimization framework introduced in Dagr´eou et al. (2022), with several improvements. In the implementation of PnPBO, all stochastic estimators for different variables can be independently incorporated, and an additional moving average technique is applied when using an unbiased estimator for the upper-level variable. In the theoretical analysis, we provide a unified convergence and complexity analysis for PnPBO, demonstrating that the adaptation of various stochastic estimators (including PAGE, ZeroSARAH, and mixed strategies) within the PnPBO framework achieves optimal sample complexity. Specifically, in the finite-sum setting, the resulting complexity matches the lower bound in Dagr´eou et al. (2024) and is comparable to that of single-level optimization (Zhou and Gu, 2019). This resolves the open question of whether the optimal complexity bounds for solving bilevel optimization are identical to those for single-level optimization. Finally, we empirically validate our framework, demonstrating its effectiveness on several benchmark problems and confirming our theoretical findings.

报告人介绍：张进教授，南方科技大学数学系/深圳国家应用数学中心教授。2007、2010年本科、硕士毕业于大连理工大学，2014年博士毕业于加拿大维多利亚大学。2015至2018年间任职香港浸会大学数学系，2019年初加入南方科技大学。致力于最优化理论和应用研究，代表性成果发表在Math Program、SIAM J Optim、Math Oper Res、SIAM J Numer Anal、Informs. J. Comput、J Mach Learn Res、IEEE Trans Pattern Anal Mach Intell,及ICML、NeurIPS、ICLR 等有重要影响力的最优化、计算数学、机器学习期刊与会议上。研究成果获得中国运筹学会青年科技奖、广东省青年科技创新奖，主持国家自然科学基金项目、广东省自然科学基金项目、深圳市科技创新培养人才项目，以及科技部重点研发计划“数学与应用数学”专项课题。