Truncated Matrix Completion - An Empirical Study

Abstract

Low-rank Matrix Completion (LRMC) describes the problem where we wish to recover missing entries of partially observed low-rank matrix. Most existing matrix completion work deals with sampling procedures that are independent of the underlying data values. While this assumption allows the derivation of nice theoretical guarantees, it seldom holds in real-world applications. In this paper, we consider various settings where the sampling mask is dependent on the underlying data values, motivated by applications in sensing, sequential decision-making, and recommender systems. Through a series of experiments, we study and compare the performance of various LRMC algorithms that were originally successful for data-independent sampling patterns.

References in corpus (6)

• A Characterization of Deterministic Sampling Patterns for Low-Rank Matrix Completion
• Matrix completion with deterministic pattern - a geometric perspective
• Rank $2r$ iterative least squares: efficient recovery of ill-conditioned low rank matrices from few entries
• Causal Matrix Completion
• Escaping Saddle Points in Ill-Conditioned Matrix Completion with a Scalable Second Order Method
• Implicit Regularization Towards Rank Minimization in ReLU Networks