Von Neumann entropy penalization and low-rank matrix estimation

DOI10.1214/11-AOS926zbMATH Open1246.62138arXiv1009.2439OpenAlexW2964300712MaRDI QIDQ449975FDOQ449975

Authors: Vladimir Koltchinskii 

Publication date: 3 September 2012

Published in: The Annals of Statistics (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/1009.2439

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

zbMATH Keywords

empirical processesquantum state tomographyvon Neumann entropymatrix regressionnoncommutative Bernstein inequalityPauli basis

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Inequalities; stochastic orderings (60E15) Applications of statistics to physics (62P35) General mathematical topics and methods in quantum theory (81Q99)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Title not available (Why is that?)
• Title not available (Why is that?)
• Exact matrix completion via convex optimization
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• Restricted strong convexity and weighted matrix completion: optimal bounds with noise
• Estimation of high-dimensional low-rank matrices
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• User-friendly tail bounds for sums of random matrices
• Title not available (Why is that?)
• Title not available (Why is that?)
• The Generic Chaining
• An Invitation to Quantum Tomography
• On almost randomizing channels with a short Kraus decomposition
• A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
• Recovering Low-Rank Matrices From Few Coefficients in Any Basis
• A simpler approach to matrix completion
• Non-asymptotic theory of random matrices: extreme singular values
• Interaction in Quantum Communication
• Sums of random Hermitian matrices and an inequality by Rudelson
• Empirical processes with a bounded \(\psi_1\) diameter
• Strong converse for identification via quantum channels
• Sparse recovery in convex hulls via entropy penalization
• Majorizing measures and proportional subsets of bounded orthonormal systems
• Empirical processes and random projections

Cited In (30)

• On signal detection and confidence sets for low rank inference problems
• Low rank estimation of similarities on graphs
• Robust Schatten-\(p\) norm based approach for tensor completion
• Title not available (Why is that?)
• Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method
• Optimal large-scale quantum state tomography with Pauli measurements
• Matrix estimation by universal singular value thresholding
• Local asymptotic equivalence of pure states ensembles and quantum Gaussian white noise
• Self-calibration and biconvex compressive sensing
• Sparse and Low-Rank Matrix Quantile Estimation With Application to Quadratic Regression
• Minimax nonparametric estimation of pure quantum states
• Noisy low-rank matrix completion with general sampling distribution
• Matrix completion via max-norm constrained optimization
• Geometric inference for general high-dimensional linear inverse problems
• Fast state tomography with optimal error bounds
• Minimax estimation of low-rank quantum states and their linear functionals
• A rank-corrected procedure for matrix completion with fixed basis coefficients
• Estimation of low rank density matrices: bounds in Schatten norms and other distances
• Rapid, robust, and reliable blind deconvolution via nonconvex optimization
• Estimation of low rank density matrices by Pauli measurements
• Nonparametric estimation of low rank matrix valued function
• Statistical inference for Bures-Wasserstein barycenters
• Asymptotic equivalence of quantum state tomography and noisy matrix completion
• Random perturbation of low rank matrices: improving classical bounds
• Optimal estimation of low rank density matrices
• Computing the entropy of a large matrix
• Pseudo-Bayesian quantum tomography with rank-adaptation
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• Convergence of the exponentiated gradient method with Armijo line search
• 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)