广州数学大讲坛第一期

第一讲——江西师范大学曾锦山教授学术报告


题目:Moreau Envelope Augmented Lagrangian Method for Nonconvex Optimization with Linear Constraints

时间:2025年1月3日(周五)晚上7:30——9:30

地点:腾讯会议(会议ID:259-198-638)

报告人:曾锦山 教授

摘要:The augmented Lagrangian method (ALM) is one of the most useful methods for constrained optimization. Its convergence has been well established under convexity assumptions or smoothness assumptions, or under both assumptions. ALM may experience oscillations and divergence when the underlying problem is simultaneously nonconvex and nonsmooth. In this talk, we consider the linearly constrained problem with a nonconvex (in particular, weakly convex) and nonsmooth objective. We modify ALM to use a Moreau envelope of the augmented Lagrangian and establish its convergence under conditions that are weaker than those in the literature. We call it the Moreau envelope augmented Lagrangian (MEAL) method. We also show that the iteration complexity of MEAL is o(ε−2) to yield an ε-accurate first-order stationary point. We establish its whole sequence convergence (regardless of the initial guess) and a rate when a Kurdyka–Łojasiewicz property is assumed. Moreover, when the subproblem of MEAL has no closed-form solution and is difficult to solve, we propose two practical variants of MEAL, an inexact version called iMEAL with an approximate proximal update, and a linearized version called LiMEAL for the constrained problem with a composite objective. Their convergence is also established.

报告人简介

曾锦山,江西师范大学计算机信息工程学院教授、博士生导师,现任计算机信息工程学院副院长、高性能计算江西省重点实验室主任、CCF科学创新论坛执委。2015年博士毕业于西安交通大学。曾先后在中国科学院电子学研究所、美国加州大学洛杉矶分校、香港科技大学和香港城市大学从事博士后或访问合作研究。2017年入选江西师范大学首批高端人才计划,2019年入选江西省重大人才计划,主持国家自然科学基金3项和江西省自然科学基金杰出青年基金1项。现已在人工智能相关领域主流期刊和会议上发表高水平论文77篇,其中JMLR和IEEE汇刊系列论文20余篇,CCF A类论文20篇。两篇论文获得“世界华人数学家联盟最佳论文奖”(2018和2020年),单篇论文连续两年入选“中国数学领域热点论文榜单前十”(排名第5(2022年)和第4(2023年)),单篇论文最高引用1359次(谷歌学术);授权发明专利16项,获批软件著作权9项。获批江西省青年教学成果奖培育项目1项,指导学生获得“挑战杯”国家特等奖等国家级学科竞赛奖励20余项,相关研究成果得到《人民日报》、《中国青年网》和《学习强国》平台等多家主流媒体的广泛报道。两度受邀在世界华人数学家大会上作四十五分钟学术报告。受邀担任国际高水平学术会议副主席或论坛主席10余次。主要研究方向是人工智能中优化理论与方法。