Subadditivity of Matrix phi-Entropy and Concentration of Random Matrices
arXiv:1308.2952 · doi:10.1214/EJP.v19-2964
Abstract
Matrix concentration inequalities provide a direct way to bound the typical spectral norm of a random matrix. The methods for establishing these results often parallel classical arguments, such as the Laplace transform method. This work develops a matrix extension of the entropy method, and it applies these ideas to obtain some matrix concentration inequalities.
arXiv comment23 pages
References in corpus (12)
- A Simpler Approach to Matrix Completion
- User-friendly tail bounds for sums of random matrices
- Concentration of the adjacency matrix and of the Laplacian in random graphs with independent edges
- Entropies, convexity, and functional inequalities
- Moment inequalities for functions of independent random variables
- Between Sobolev and Poincaré
- Matrix concentration inequalities via the method of exchangeable pairs
- Noncommutative Bennett and Rosenthal inequalities
- Binomial-Poisson entropic inequalities and the M/M/ queue
- A Note on Element-wise Matrix Sparsification via a Matrix-valued Bernstein Inequality
- Characterisation of matrix entropies
- Deriving Matrix Concentration Inequalities from Kernel Couplings
Cited by in corpus (9)
- On the joint convexity of the Bregman divergence of matrices
- Exponential Decay of Matrix -Entropies on Markov Semigroups with Applications to Dynamical Evolutions of Quantum Ensembles
- Matrix Poincaré, Φ-Sobolev inequalities, and quantum ensembles
- Nonlinear Matrix Concentration via Semigroup Methods
- From Poincaré Inequalities to Nonlinear Matrix Concentration
- A Matrix Bernstein Inequality for Strong Rayleigh Distributions
- Jointly convex quantum Jensen divergences
- A note on quantum entropy
- Some operator convex functions of several variables