REVIEW 5 cited by
Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent
read the original abstract
We address the rectangular matrix completion problem by lifting the unknown matrix to a positive semidefinite matrix in higher dimension, and optimizing a nonconvex objective over the semidefinite factor using a simple gradient descent scheme. With $O( \mu r^2 \kappa^2 n \max(\mu, \log n))$ random observations of a $n_1 \times n_2$ $\mu$-incoherent matrix of rank $r$ and condition number $\kappa$, where $n = \max(n_1, n_2)$, the algorithm linearly converges to the global optimum with high probability.
Forward citations
Cited by 5 Pith papers
-
Sample-efficient inductive matrix completion with noise and inexact side-information
Nonconvex projected gradient descent for noisy inductive matrix completion achieves linear convergence and order-optimal error at sample complexity scaling with side-information dimension a instead of ambient dimension n.
-
Sample-efficient inductive matrix completion with noise and inexact side-information
A projected gradient descent algorithm for noisy inductive matrix completion achieves linear convergence and stable recovery at sample complexity governed by side-information dimension, extending to inexact side-infor...
-
Learning Nonlinear Factor Models with Unknown Monotone Links from Incomplete and Noisy Data
Proposes BCD algorithm with regularization for joint recovery of low-rank factors, loadings, and monotone RKHS link from incomplete noisy observations, with convergence guarantees under incoherence conditions.
-
Latent Structural Categorical Matrix Completion with Application to Quasispecies Analysis
LCMC performs categorical matrix completion via latent tensor factorization in a double-loop setup with adaptive dimension estimation and split-merge-refine enhancements, outperforming prior methods on synthetic and q...
-
Convexity in Disguise: A Theoretical Framework for Nonconvex Low-Rank Matrix Estimation
Nonconvex low-rank matrix estimation procedures are shown to be equivalent to locally strongly convex formulations via a benign regularizer that does not change the algorithm's update rule.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.