A Max-Norm Constrained Minimization Approach to 1-Bit Matrix Completion
From MaRDI portal
Abstract: We consider in this paper the problem of noisy 1-bit matrix completion under a general non-uniform sampling distribution using the max-norm as a convex relaxation for the rank. A max-norm constrained maximum likelihood estimate is introduced and studied. The rate of convergence for the estimate is obtained. Information-theoretical methods are used to establish a minimax lower bound under the general sampling model. The minimax upper and lower bounds together yield the optimal rate of convergence for the Frobenius norm loss. Computational algorithms and numerical performance are also discussed.
Recommendations
- 1-bit matrix completion
- Matrix completion via max-norm constrained optimization
- 1-bit matrix completion: PAC-Bayesian analysis of a variational approximation
- The \(N_{0}^{1}\)-matrix completion problem
- Exact matrix completion via convex optimization
- An alternating minimization method for matrix completion problems
- One-Bit Compressive Sensing via Schur-Concave Function Minimization
- Matrix completion via minimizing an approximate rank
- The Power of Convex Relaxation: Near-Optimal Matrix Completion
- Characterization of \(\ell_1\) minimizer in one-bit compressed sensing
Cited in
(30)- Adaptive multinomial matrix completion
- Item response theory -- a statistical framework for educational and psychological measurement
- Misclassification excess risk bounds for 1-bit matrix completion
- Maximum a posteriori inference of random dot product graphs via conic programming
- 1-bit matrix completion
- 1-bit matrix completion: PAC-Bayesian analysis of a variational approximation
- Flexible low-rank statistical modeling with missing data and side information
- Concentration properties of fractional posterior in 1-bit matrix completion
- scientific article; zbMATH DE number 7164697 (Why is no real title available?)
- High-dimensional large-scale mixed-type data imputation under missing at random
- One-bit tensor completion via transformed tensor singular value decomposition
- Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions
- Collective matrix completion
- A nonlinear matrix decomposition for mining the zeros of sparse data
- Joint maximum likelihood estimation for high-dimensional exploratory item factor analysis
- Matrix completion via max-norm constrained optimization
- Matrix completion from a computational statistics perspective
- scientific article; zbMATH DE number 7306859 (Why is no real title available?)
- Online network change point detection with missing values and temporal dependence
- Imputation and low-rank estimation with missing not at random data
- Statistical inference for covariate-adjusted and interpretable generalized latent factor model with application to testing fairness
- Uniform recovery guarantees for quantized corrupted sensing using structured or generative priors
- Generalized high-dimensional trace regression via nuclear norm regularization
- scientific article; zbMATH DE number 7370528 (Why is no real title available?)
- Structured latent factor analysis for large-scale data: identifiability, estimability, and their implications
- A Majorization-Minimization Gauss-Newton Method for 1-Bit Matrix Completion
- Convergence of the majorized PAM method with subspace correction for low-rank composite factorization model
- Main effects and interactions in mixed and incomplete data frames
- Algebraic-based primal interior-point algorithms for stochastic infinity norm optimization
- Online optimization for max-norm regularization
This page was built for publication: A Max-Norm Constrained Minimization Approach to 1-Bit Matrix Completion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2933966)
