A Riemannian rank-adaptive method for low-rank matrix completion

Watch Video

02 24, 2022


Speaker: Bin Gao (University of Münster)
Title: A Riemannian rank-adaptive method for low-rank matrix completion
Date: 2022-02-24 Thursday 14:30-15:30pm (Time in Beijing)
Tencent Meeting :817 977 686
Abstract :In this talk, we consider the low-rank matrix completion problem which has been extensively studied in recent years. This problem can be solved by Riemannian optimization on a fixed-rank manifold. However, a drawback of the known approaches is that the rank parameter has to be fixed a priori. Instead, we consider the optimization problem on the set of bounded-rank matrices. We propose a Riemannian rank-adaptive method, which consists of fixed-rank optimization, rank increase step and rank reduction step.  We explore its performance applied to the low-rank matrix completion problem. Numerical experiments on synthetic and real-world datasets illustrate that the proposed rank-adaptive method compares favorably with state-of-the-art algorithms.This is a joint work with P.-A. Absil.



Copyright@2008,All Rights Reserved, Academy of Mathematics and Systems Science,CAS
Tel:86-10-82541777 Fax: 86-10-82541972 E-mail: contact@amss.ac.cn
京ICP备05002806-1号 京公网安备110402500020号