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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 601–650 of 796 papers

TitleStatusHype
On the Predictability of Human Assessment: when Matrix Completion Meets NLP Evaluation—0
On the properties of variational approximations of Gibbs posteriors—0
On the simplicity and conditioning of low rank semidefinite programs—0
On the Robustness of Cross-Concentrated Sampling for Matrix Completion—0
Optimal (0,1)-Matrix Completion with Majorization Ordered Objectives (To the memory of Pravin Varaiya)—0
Optimal Exact Matrix Completion Under new Parametrization—0
Optimal Algorithms for Latent Bandits with Cluster Structure—0
Disjunctive Branch-And-Bound for Certifiably Optimal Low-Rank Matrix Completion—0
Optimal Low-Rank Tensor Recovery from Separable Measurements: Four Contractions Suffice—0
Optimal Transfer Learning for Missing Not-at-Random Matrix Completion—0
Optimal Transport with Heterogeneously Missing Data—0
Optimized Waveform Design for OFDM-based ISAC Systems Under Limited Resource Occupancy—0
Optimum Codesign for Image Denoising Between Type-2 Fuzzy Identifier and Matrix Completion Denoiser—0
Orthogonal Inductive Matrix Completion—0
PAC-Bayesian matrix completion with a spectral scaled Student prior—0
Parametric Models for Mutual Kernel Matrix Completion—0
Partial Matrix Completion—0
Penalty Decomposition Methods for Rank Minimization—0
Perturbation Analysis of Randomized SVD and its Applications to Statistics—0
Phase transitions and sample complexity in Bayes-optimal matrix factorization—0
Poisson Matrix Completion—0
Poisson Matrix Recovery and Completion—0
Polynomial Matrix Completion for Missing Data Imputation and Transductive Learning—0
Polynomial Precision Dependence Solutions to Alignment Research Center Matrix Completion Problems—0
Power-Flow-Embedded Projection Conic Matrix Completion for Low-Observable Distribution Systems—0
Practical Matrix Completion and Corruption Recovery using Proximal Alternating Robust Subspace Minimization—0
Prediction and Quantification of Individual Athletic Performance—0
Prediction with Unpredictable Feature Evolution—0
Preference Completion from Partial Rankings—0
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates—0
Probabilistic low-rank matrix completion on finite alphabets—0
Probabilistic Low-Rank Matrix Completion with Adaptive Spectral Regularization Algorithms—0
Prognostics of Surgical Site Infections using Dynamic Health Data—0
Progresses and Challenges in Link Prediction—0
Projected Wirtinger Gradient Descent for Low-Rank Hankel Matrix Completion in Spectral Compressed Sensing—0
Projection-Free Algorithm for Stochastic Bi-level Optimization—0
Projection-Free Bandit Convex Optimization—0
Propagation Map Reconstruction via Interpolation Assisted Matrix Completion—0
Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent—0
Provable Inductive Matrix Completion—0
Provable Low Rank Plus Sparse Matrix Separation Via Nonconvex Regularizers—0
Provable Non-linear Inductive Matrix Completion—0
Provable Tensor-Train Format Tensor Completion by Riemannian Optimization—0
Proximal Riemannian Pursuit for Large-Scale Trace-Norm Minimization—0
Pseudo-Bayesian Robust PCA: Algorithms and Analyses—0
PU Learning for Matrix Completion—0
Quantized Matrix Completion for Personalized Learning—0
Quantizing Heavy-tailed Data in Statistical Estimation: (Near) Minimax Rates, Covariate Quantization, and Uniform Recovery—0
Quaternion Matrix Completion Using Untrained Quaternion Convolutional Neural Network for Color Image Inpainting—0
Quaternion Optimized Model with Sparse Regularization for Color Image Recovery—0
Show:102550
← PrevPage 13 of 16Next →

No leaderboard results yet.