报告题目：A Note on the Convergence of ADMM

报告人：陈亮

时间：2016-07-26

地点：英国威廉希尔公司北阶梯教室

摘要：This note serves two purposes. Firstly, we construct a counterexample to show that the statement on the convergence of the alternating direction method of multipliers (ADMM) for solving linearly constrained convex optimization problems in a highly influential paper by Boyd et al. [Found. Trends Mach. Learn. 3(1) 1-122 (2011)] can be false if no prior condition on the existence of solutions to all the subproblems involved is assumed to hold. Secondly, we present fairly mild conditions to guarantee the existence of solutions to all the subproblems of the ADMM and provide a rigorous convergence analysis on the ADMM with a computationally more attractive large step-length that can even exceed the practically much preferred golden ratio of 1.618

报告时间：7月26日上午8:30-11:30

报告人简 介：报告人自2008年起从事数值最优化方面有关问题的研究，期间赴新加坡国立大学数学系公派联合培养两年，主要研究的方向是求解约束最优化问题的基于增广拉格朗日的方法及理论分析，目前的一些研究成果已在《Math. Program.》,《J. Optim. Theory Appl.》等专业领域内具有代表性的杂志发表, 并担任《SIAM J. Optim》,《Optim.Method Softw.》等业内杂志的审稿人。