SOTAVerified

Low-Rank Matrix Completion

Low-Rank Matrix Completion is an important problem with several applications in areas such as recommendation systems, sketching, and quantum tomography. The goal in matrix completion is to recover a low rank matrix, given a small number of entries of the matrix.

Source: Universal Matrix Completion

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 141–150 of 158 papers

TitleStatusHype
Secrets of Matrix Factorization: Approximations, Numerics, Manifold Optimization and Random Restarts—0
Efficient Compression of Overparameterized Deep Models through Low-Dimensional Learning DynamicsCode0
Guaranteed Rank Minimization via Singular Value ProjectionCode0
Depth Image Inpainting: Improving Low Rank Matrix Completion with Low Gradient RegularizationCode0
Riemannian stochastic variance reduced gradient algorithm with retraction and vector transportCode0
Efficient and Robust Freeway Traffic Speed Estimation under Oblique Grid using Vehicle Trajectory DataCode0
Algebraic Variety Models for High-Rank Matrix CompletionCode0
Mixed Membership Graph Clustering via Systematic Edge QueryCode0
A Gradient Descent Algorithm on the Grassman Manifold for Matrix CompletionCode0
Adaptive Matrix Completion for the Users and the Items in TailCode0
Show:102550
← PrevPage 15 of 16Next →

No leaderboard results yet.