报告人：Prof.Linglong Kong (加拿大University of Alberta数学与统计学系)
报告摘要：Many problems in science and engineering can be reduced to the recovery of an unknown large matrix from a small number of random linear measurements. Matrix factorization arguably is the most popular approach for low-rank matrix recovery. Many methods have been proposed using different loss functions, such as the most widely used L2 loss, more robust hoices L1 and Huber loss, and quantile and expectile loss for kewed data. All of them can be unified into the framework of Mestimation. In this paper, we present a general framework of lowrank matrix factorization based on M-estimation in statistics. The framework mainly involves two steps: we first apply Nesterov’s smoothing technique to obtain an optimal smooth approximation for non-smooth loss functions, such as L1 and quantile loss; secondly, we exploit an alternative updating scheme along with Nesterov’s momentum method at each step to minimize the smoothed loss function. Strong theoretical convergence guarantee has been developed for the general framework, and extensive numerical experiments have been conducted to illustrate the performance of the proposed algorithm.
会议时间：2020/7/16 09:00-11:30
点击链接直接加入会议：
https://meeting.tencent.com/s/u1hJdnVG2y2D
会议 ID：698 433 360
手机一键拨号入会
+8675536550000,,698433360# (中国大陆)
+85230018898,,,2,698433360# (中国香港)
根据您的位置拨号
+8675536550000 (中国大陆)
+85230018898 (中国香港)