IT경영 분야 세미나를 아래와 같이 개최하오니, 관심 있는 분들의 많은 참석 부탁 드립니다.

1. 일시: 2019년 3월 14일(목), 16:00~17:20
2. 장소: 수펙스경영관 101 강의실
3. 강사: 김동규 교수 (KAIST)
4. 주제: Matrix Completion (Netflix Problem): Intelligent Initialization and Adaptive Thresholding for Iterative Matrix Completion
5. 연구분야: IT경영 분야
* Lecture will be delivered in Korean.
* Seminar materials: Abstract

Abstract:
Over the past decade, various matrix completion algorithms have been developed. Thresholded singular value decomposition (SVD) is a popular technique in implementing many of them. A sizable number of studies have shown its theoretical and empirical excellence, but choosing the right threshold level still remains as a key empirical difficulty. This article proposes a novel matrix completion algorithm which iterates thresholded SVD with theoretically justified and data-dependent values of thresholding parameters. The estimate of the proposed algorithm enjoys the minimax error rate and shows outstanding empirical performances. The thresholding scheme that we use can be viewed as a solution to a nonconvex optimization problem, understanding of whose theoretical convergence guarantee is known to be limited. We investigate this problem by introducing a simpler algorithm, generalized- softImpute , analyzing its convergence behavior, and connecting it to the proposed algorithm.