Bernstein-type and Bennett-type inequalities for unbounded matrix martingales

2024/11/12 by Kroshnin, Alexey, Suvorikova, Alexandra
#60E15 #FOS: Mathematics #Probability (math.PR) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.2411.07878

Abstract

We derive explicit Bernstein-type and Bennett-type concentration inequalities for matrix-valued martingale processes with unbounded observations from the Hermitian space ℍ(d). Specifically, we assume that the ψ_α-Orlicz (quasi-)norms of their difference process are bounded for some α> 0. Further, we generalize the obtained result by replacing the ambient dimension d with the effective rank of the covariance of the observations. To illustrate the applicability of the results, we prove several corollaries, including an empirical version of Bernstein's inequality and an extension of the bounded difference inequality, also known as McDiarmid's inequality.

Related

• On Bernstein Type Exponential Inequalities for Matrix Martingales
• Matrix Moment and Concentration Inequalities for Martingales and Ergodic Markov Chains with Applications in Statistical Learning
• Concentration for matrix martingales in continuous time and microscopic\n activity of social networks
• Dzhaparidze-van Zanten type inequalities for self-normalized martingales
• A note on concentration inequality for vector-valued martingales with weak exponential-type tails