English

On the Robustness of Cross-Concentrated Sampling for Matrix Completion

Machine Learning 2025-04-17 v1 Information Theory Machine Learning math.IT Optimization and Control

Abstract

Matrix completion is one of the crucial tools in modern data science research. Recently, a novel sampling model for matrix completion coined cross-concentrated sampling (CCS) has caught much attention. However, the robustness of the CCS model against sparse outliers remains unclear in the existing studies. In this paper, we aim to answer this question by exploring a novel Robust CCS Completion problem. A highly efficient non-convex iterative algorithm, dubbed Robust CUR Completion (RCURC), is proposed. The empirical performance of the proposed algorithm, in terms of both efficiency and robustness, is verified in synthetic and real datasets.

Keywords

Cite

@article{arxiv.2401.15566,
  title  = {On the Robustness of Cross-Concentrated Sampling for Matrix Completion},
  author = {HanQin Cai and Longxiu Huang and Chandra Kundu and Bowen Su},
  journal= {arXiv preprint arXiv:2401.15566},
  year   = {2025}
}

Comments

58th Annual Conference of Information Sciences and Systems

R2 v1 2026-06-28T14:29:14.458Z