A Deterministic Theory of Low Rank Matrix Completion
From MaRDI portal
Abstract: The problem of completing a large low rank matrix using a subset of revealed entries has received much attention in the last ten years. The main result of this paper gives a necessary and sufficient condition, stated in the language of graph limit theory, for a sequence of matrix completion problems with arbitrary missing patterns to be asymptotically solvable. It is then shown that a small modification of the Cand`es-Recht nuclear norm minimization algorithm provides the required asymptotic solution whenever the sequence of problems is asymptotically solvable. The theory is fully deterministic, with no assumption of randomness. A number of open questions are listed.
Cited in
(11)- Low-rank matrix completion in a general non-orthogonal basis
- Matrix completion for matrices with low-rank displacement
- Completing any low-rank matrix, provably
- Low-Rank Matrix Completion in the Presence of High Coherence
- A universal rank approximation method for matrix completion
- Deterministic tensor completion with hypergraph expanders
- Deterministic and Probabilistic Conditions for Finite Completability of Low-Tucker-Rank Tensor
- Low-Complexity Modeling of Partially Available Second-Order Statistics: Theory and an Efficient Matrix Completion Algorithm
- A lower bound guaranteeing exact matrix completion via singular value thresholding algorithm
- Nuclear norm regularization
- Robust Matrix Completion with Heavy-Tailed Noise
This page was built for publication: A Deterministic Theory of Low Rank Matrix Completion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5138947)