报告人：王浩博士、助理教授，上海科技大学

报告人简介：王浩博士于2015年5月在美国Lehigh University工业工程系获得博士学位，并于2010年和2007年在北京航空航天大学数学与应用数学系分别获得理学硕士和学士学位。王浩博士于2016年3月以助理教授加入上海科技大学信息与技术学院。当前研究领域主要为惩罚算法、非精确算法、正则化问题等。

报告题目：Efficient Projection onto Nonconvex Lp Balls

报告摘要：This paper primarily focuses on computing the Euclidean projection of a vector onto the Lp ball in which p ∈ (0, 1). Such a problem emerges as the core building block in statistical machine learning and signal processing tasks because of its ability to promote sparsity. However, efficient numerical algorithms for finding the projections are still not available, particularly in large-scale optimization. To handle this challenge, we first derive the first-order necessary optimality conditions of this problem using Frechet normal cone. Based on this characterization, we develop a novel numerical approach for computing the stationary point through solving a sequence of projections onto the reweighted l1-balls. This method is practically simple to implement and computationally efficient. Moreover, the proposed algorithm is shown to converge uniquely under mild conditions and has a worst-case convergence rate. Numerical experiments demonstrate the efficiency of our proposed algorithm.

报告时间：2021年6月20日 14:00-16:00

报告地点：理学楼609