Freedman's inequality for matrix martingales

Abstract

Freedman's inequality is a martingale counterpart to Bernstein's inequality. This result shows that the large-deviation behavior of a martingale is controlled by the predictable quadratic variation and a uniform upper bound for the martingale difference sequence. Oliveira has recently established a natural extension of Freedman's inequality that provides tail bounds for the maximum singular value of a matrix-valued martingale. This note describes a different proof of the matrix Freedman inequality that depends on a deep theorem of Lieb from matrix analysis. This argument delivers sharp constants in the matrix Freedman inequality, and it also yields tail bounds for other types of matrix martingales. The new techniques are adapted from recent work by the present author.

8 pages. This note contains some martingale results that were presented in "User-friendly tail bounds for sums of random matrices" (arXiv:1004.4389). These results have been removed from the original article

References in corpus (1)

• Concentration of the adjacency matrix and of the Laplacian in random graphs with independent edges

Cited by in corpus (6)

• Dimension-free tail inequalities for sums of random matrices
• Concentration of OTOC and Lieb-Robinson velocity in random Hamiltonians
• Solving Directed Laplacian Systems in Nearly-Linear Time through Sparse LU Factorizations
• Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits
• Learning Markov models via low-rank optimization
• On Learning to Rank Long Sequences with Contextual Bandits