Structured matrix estimation and completion
From MaRDI portal
Publication:2325396
Abstract: We study the problem of matrix estimation and matrix completion under a general framework. This framework includes several important models as special cases such as the gaussian mixture model, mixed membership model, bi-clustering model and dictionary learning. We consider the optimal convergence rates in a minimax sense for estimation of the signal matrix under the Frobenius norm and under the spectral norm. As a consequence of our general result we obtain minimax optimal rates of convergence for various special models.
Recommendations
Cites work
- A spectral algorithm for learning mixture models
- A tail inequality for quadratic forms of subgaussian random vectors
- Database-friendly random projections: Johnson-Lindenstrauss with binary coins.
- Exponential screening and optimal rates of sparse estimation
- scientific article; zbMATH DE number 6388313 (Why is no real title available?)
- Information-theoretic determination of minimax rates of convergence
- Introduction to nonparametric estimation
- Learning mixtures of spherical Gaussians: moment methods and spectral decompositions (extended abstract)
- Matrix completion from noisy entries
- Matrix completion via max-norm constrained optimization
- Matrix estimation by universal singular value thresholding
- Mixed membership stochastic blockmodels
- Noisy low-rank matrix completion with general sampling distribution
- Noisy Matrix Completion Under Sparse Factor Models
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- Optimal estimation and completion of matrices with biclustering structures
- Optimal selection of reduced rank estimators of high-dimensional matrices
- Oracle inequalities for network models and sparse graphon estimation
- Polynomial Learning of Distribution Families
- Rank penalized estimators for high-dimensional matrices
- Rate-optimal graphon estimation
- Recovering Low-Rank Matrices From Few Coefficients in Any Basis
- Restricted strong convexity and weighted matrix completion: optimal bounds with noise
- Sharp nonasymptotic bounds on the norm of random matrices with independent entries
- Structured matrix estimation and completion
- The Power of Convex Relaxation: Near-Optimal Matrix Completion
Cited in
(20)- Robust low-rank matrix estimation
- Matrix factorization for multivariate time series analysis
- Minimax rates in network analysis: graphon estimation, community detection and hypothesis testing
- An adaptation for iterative structured matrix completion
- The hierarchy of block models
- High-dimensional VAR with low-rank transition
- A general framework for Bayes structured linear models
- Structured matrix estimation and completion
- Matrix completion with sparse measurement errors
- Optimal estimation and completion of matrices with biclustering structures
- Estimation of matrices with row sparsity
- Poisson Matrix Recovery and Completion
- Statistical Methods for Minimax Estimation in Linear Models with Unknown Design Over Finite Alphabets
- Collective matrix completion
- Low-Complexity Modeling of Partially Available Second-Order Statistics: Theory and an Efficient Matrix Completion Algorithm
- Optimal cleaning for singular values of cross-covariance matrices
- Optimal estimation and computational limit of low-rank Gaussian mixtures
- Robust matrix completion
- Low-rank regularization in two-sided matrix regression
- Trend of high dimensional time series estimation using low-rank matrix factorization: heuristics and numerical experiments via the \texttt{TrendTM} package
This page was built for publication: Structured matrix estimation and completion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2325396)
