Von Neumann entropy penalization and low-rank matrix estimation
From MaRDI portal
Publication:449975
DOI10.1214/11-AOS926zbMATH Open1246.62138OpenAlexW2964300712MaRDI QIDQ449975FDOQ449975
Abstract: A problem of statistical estimation of a Hermitian nonnegatively definite matrix of unit trace (for instance, a density matrix in quantum state tomography) is studied. The approach is based on penalized least squares method with a complexity penalty defined in terms of von Neumann entropy. A number of oracle inequalities have been proved showing how the error of the estimator depends on the rank and other characteristics of the oracles. The methods of proofs are based on empirical processes theory and probabilistic inequalities for random matrices, in particular, noncommutative versions of Bernstein inequality.
Recommendations
- Estimation of the multivariate normal precision matrix under the entropy loss
- Estimation of low-rank matrices via approximate message passing
- Estimation of high-dimensional low-rank matrices
- Rank penalized estimators for high-dimensional matrices
- Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications
- Estimation of (near) low-rank matrices with noise and high-dimensional scaling
- Probabilistic low-rank matrix completion from quantized measurements
- Optimal estimation of low rank density matrices
- An entropic estimator for linear inverse problems
Cites work
- scientific article; zbMATH DE number 1579275 (Why is no real title available?)
- scientific article; zbMATH DE number 3658507 (Why is no real title available?)
- scientific article; zbMATH DE number 49190 (Why is no real title available?)
- scientific article; zbMATH DE number 967931 (Why is no real title available?)
- A simpler approach to matrix completion
- A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
- An Invitation to Quantum Tomography
- Empirical processes and random projections
- Empirical processes with a bounded \(\psi_1\) diameter
- Estimation of high-dimensional low-rank matrices
- Exact matrix completion via convex optimization
- Interaction in Quantum Communication
- Majorizing measures and proportional subsets of bounded orthonormal systems
- Non-asymptotic theory of random matrices: extreme singular values
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- On almost randomizing channels with a short Kraus decomposition
- Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
- Recovering Low-Rank Matrices From Few Coefficients in Any Basis
- Restricted strong convexity and weighted matrix completion: optimal bounds with noise
- Sparse recovery in convex hulls via entropy penalization
- Strong converse for identification via quantum channels
- Sums of random Hermitian matrices and an inequality by Rudelson
- The Generic Chaining
- The Power of Convex Relaxation: Near-Optimal Matrix Completion
- Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
- User-friendly tail bounds for sums of random matrices
- Weak convergence and empirical processes. With applications to statistics
Cited in
(30)- Self-calibration and biconvex compressive sensing
- Low rank estimation of similarities on graphs
- On signal detection and confidence sets for low rank inference problems
- Pseudo-Bayesian quantum tomography with rank-adaptation
- Optimal estimation of low rank density matrices
- Estimation of low rank density matrices by Pauli measurements
- Computing the entropy of a large matrix
- Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method
- Sparse and Low-Rank Matrix Quantile Estimation With Application to Quadratic Regression
- Optimal large-scale quantum state tomography with Pauli measurements
- Noisy low-rank matrix completion with general sampling distribution
- Random perturbation of low rank matrices: improving classical bounds
- Matrix estimation by universal singular value thresholding
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- Robust Schatten-\(p\) norm based approach for tensor completion
- Convergence of the exponentiated gradient method with Armijo line search
- Minimax estimation of low-rank quantum states and their linear functionals
- scientific article; zbMATH DE number 7370563 (Why is no real title available?)
- Minimax nonparametric estimation of pure quantum states
- Asymptotic equivalence of quantum state tomography and noisy matrix completion
- Matrix completion via max-norm constrained optimization
- Geometric inference for general high-dimensional linear inverse problems
- A rank-corrected procedure for matrix completion with fixed basis coefficients
- Estimation of low rank density matrices: bounds in Schatten norms and other distances
- Local asymptotic equivalence of pure states ensembles and quantum Gaussian white noise
- Nonparametric estimation of low rank matrix valued function
- Rapid, robust, and reliable blind deconvolution via nonconvex optimization
- Fast state tomography with optimal error bounds
- Statistical inference for Bures-Wasserstein barycenters
- Self-calibration and bilinear inverse problems via linear least squares
This page was built for publication: Von Neumann entropy penalization and low-rank matrix estimation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q449975)
