A novel initialization method of fixed point continuation for recommendation systems

作者：

Highlights：

• A property in the iterative process of FPC is discovered.

• A novel initialization method of FPC is proposed.

• A strategy to improve the efficiency of FPC is given.

• The method makes the recommendation algorithm have a high convergence speed.

摘要

•A property in the iterative process of FPC is discovered.•A novel initialization method of FPC is proposed.•A strategy to improve the efficiency of FPC is given.•The method makes the recommendation algorithm have a high convergence speed.

论文关键词：Matrix completion,Nuclear norm minimization,Fixed point continuation,Recommended systems,Initialization

论文评审过程：Received 5 May 2022, Revised 14 July 2022, Accepted 30 July 2022, Available online 4 August 2022, Version of Record 15 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118346