SOTAVerified

Matrix Completion

Matrix Completion is a method for recovering lost information. It originates from machine learning and usually deals with highly sparse matrices. Missing or unknown data is estimated using the low-rank matrix of the known data.

Source: A Fast Matrix-Completion-Based Approach for Recommendation Systems

Papers

Showing 726750 of 796 papers

TitleStatusHype
On Tensor Completion via Nuclear Norm Minimization0
A Comparison of Clustering and Missing Data Methods for Health Sciences0
Advancing Matrix Completion by Modeling Extra Structures beyond Low-Rankness0
Geometric Inference for General High-Dimensional Linear Inverse Problems0
Orthogonal Rank-One Matrix Pursuit for Low Rank Matrix CompletionCode0
CUR Algorithm with Incomplete Matrix Observation0
New Perspectives on k-Support and Cluster Norms0
Computational Limits for Matrix Completion0
Universal Matrix Completion0
Phase transitions and sample complexity in Bayes-optimal matrix factorization0
Low-Rank Modeling and Its Applications in Image Analysis0
Online Matrix Completion Through Nuclear Norm Regularisation0
Understanding Alternating Minimization for Matrix Completion0
Matrix Completion From any Given Set of Observations0
Error-Minimizing Estimates and Universal Entry-Wise Error Bounds for Low-Rank Matrix Completion0
Speedup Matrix Completion with Side Information: Application to Multi-Label Learning0
Probabilistic Low-Rank Matrix Completion with Adaptive Spectral Regularization Algorithms0
A Novel Two-Step Method for Cross Language Representation Learning0
Learning Mixtures of Discrete Product Distributions using Spectral Decompositions0
The Noisy Power Method: A Meta Algorithm with Applications0
Identifying Influential Entries in a Matrix0
Unsupervised Spectral Learning of WCFG as Low-rank Matrix Completion0
Incoherence-Optimal Matrix Completion0
Online Algorithms for Factorization-Based Structure from Motion0
A Max-Norm Constrained Minimization Approach to 1-Bit Matrix Completion0
Show:102550
← PrevPage 30 of 32Next →

No leaderboard results yet.