Learned Robust Matrix Completion via Deep Unfolding
LRMC is a scalable non-convex algorithm for robust matrix completion (recovering a low-rank matrix from data that is both incomplete and outlier-corrupted) with proven linear convergence. Its free parameters are learned by deep unfolding — unrolling the iterative solver into a trainable network — and a feedforward-recurrent-mixed network extends unfolding from a fixed iteration count to effectively infinite iterations, beating prior methods on video background subtraction, ultrasound imaging, face modeling, and satellite cloud removal.
Deeply Learned Robust Matrix Completion for Large-scale Low-rank Data Recovery
Robust matrix completion (RMC) recovers a low-rank matrix when entries are both missing and corrupted by extreme outliers — a common situation in large-scale data analysis. This paper introduces Lear…