学术报告
报告题目: Randomly permuted ADMM and subspace Optimization methods
报 告 人：贲树军 博士（中国科学院数学与系统科学研究院）
报告时间： 2015年5月8日下午3:00--5:00
报告地点：4号楼 4318室
欢迎广大师生参加。
数学学院
2015年5月4日
报告摘要： This talk is concerned with large scale optimization problems arising in data
analysis, machine learning and other areas of current interest. A popular and easy way
to deal with these large scale optimization problems is to solve the large scale subproblems approximately by some certain simple methods, which aims to reduce the computation and storage cost. In this talk, I first introduce randomly permuted ADMM for these problems, which in each step randomly and independently permutes the updating order of any given number of blocks, and then updates the Lagrange multiplier. Then, I introduce the subspace optimization method that constructs a subproblem in low dimensions in each iteration so that the computation cost is reduced much more than the standard approaches do. This offers a possible way to handle large scale optimization problems.