报告题目：A Single-Loop Algorithm for Decentralized Bilevel Optimization
主讲人：杨俊锋教授（南京大学）
时间：2026年1月14日（周三）16:00 p.m.
地点：北院卓远楼305会议室
主办单位：统计与数学学院
摘要：
Bilevel optimization (BO) has gained significant attention in recent years due to its broad applications in machine learning. In this talk, we focus on decentralized BO and proposes a novel single-loop algorithm for solving it with a strongly convex lower-level problem. Our approach is a fully single-loop method that approximates the hypergradient using only two matrix-vector multiplications per iteration. Our algorithm does not require any gradient heterogeneity assumption and achieves the best-known convergence rate for BO algorithms. We also present experimental results on hyperparameter optimization problems using both synthetic and MNIST datasets, which demonstrate the efficiency of our proposed algorithm. （Joint with Dong Youran, Ma Shiqian, and Yin Chao)
主讲人简介：
杨俊锋，南京大学数学学院，教授，博导。主要从事最优化计算方法及其应用研究，代表性工作发表在SIAM J. Optimization、Mathematics of Operations Research、SIAM J. Scientific Computing、Mathematics of Computation、SIAM J. Imaging Sciences、Inverse Problems等期刊，开发图像去模糊软代码包FTVd, 压缩感知一模解码代码包YALL1等。2016年获中国运筹学会青年科技奖，2012 年入选教育部新世纪优秀人才支持计划等。
滇公网安备53010202000350号滇ICP备17008047号 Copyright © 2013 Yunnan University of Finance and Economics All Rights Reserved
