Math Graduate Student Seminar, Chandra Kundu, Mathematics, UCF

Title: Large-Scale Robust Matrix Completion Via Deep Unfolding

Abstract: Principal Component Analysis (PCA) is a well-established technique for dimensionality reduction in statistics and machine learning. However, its wellknown limitations include sensitivity to outliers and an inability to handle incomplete data which is quote common in real-world dataset. To address these two limitations simultaneously, the problem of Robust Matrix Completion (RMC) has been propsed. In this study, we introduce a deep-learning-augmented approach to RMC, called Learned Robust Matrix Completion (LRMC), through a process known as learning to optimize or deep unfolding.