Deeply Learned Robust Matrix Completion for Large-scale Low-rank Data Recovery

HanQin Cai, Chandra Kundu, Jialin Liu, Wotao Yin
12/31/2024
cs.LGcs.CVcs.IT

No official code found. Best implementation: chandrakundu/LRMC (4 stars, MIT, last commit 2025-10-09).

Abstract

Robust matrix completion (RMC) is a widely used machine learning tool that simultaneously tackles two critical issues in low-rank data analysis: missing data entries and extreme outliers. This paper proposes a novel scalable and learnable non-convex approach, coined Learned Robust Matrix Completion (LRMC), for large-scale RMC problems. LRMC enjoys low computational complexity with linear convergence. Motivated by the proposed theorem, the free parameters of LRMC can be effectively learned via deep unfolding to achieve optimum performance. Furthermore, this paper proposes a flexible feedforward-recurrent-mixed neural network framework that extends deep unfolding from fix-number iterations to infinite iterations. The superior empirical performance of LRMC is verified with extensive experiments against state-of-the-art on synthetic datasets and real applications, including video background subtraction, ultrasound imaging, face modeling, and cloud removal from satellite imagery.

View on arXivView PDF

Code Implementations(1)

chandrakundu/LRMCCommunity77%
MIT

Deeply Learned Robust Matrix Completion for Large-scale Low-rank Data Recovery

40C, C++Jan 1, 20251 years agoMIT
cloud-removaldeep-unfoldingdeep-unrollingface-modelinglearning-to-optimize+1 more

Similar Papers

Matrix Completion via Nonsmooth Regularization of Fully Connected Neural Networks

81% match2024

Linear Recursive Feature Machines provably recover low-rank matrices

80% match1 repo172024

Tailed Low-Rank Matrix Factorization for Similarity Matrix Completion

79% match2024

Deep Unrolling for Nonconvex Robust Principal Component Analysis

79% match2023

Robust Methods for High-Dimensional Linear Learning

79% match2022

Generalized Low-Rank Matrix Completion Model with Overlapping Group Error Representation

78% match2024

Cite this paper

@article{cai2024deeply,
  title  = {Deeply Learned Robust Matrix Completion for Large-scale Low-rank Data Recovery},
  author = {HanQin Cai and Chandra Kundu and Jialin Liu and Wotao Yin},
  year   = {2024},
  eprint = {2501.00677},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.00677v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.00677.svg)](https://codeofpaper.com/paper/2501.00677)

Discussion