New insights on concentration inequalities for self-normalized martingales

DOI10.1214/19-ECP269MaRDI QIDQ2332992zbMATH OpenOpenAlexFDO

Authors Bernard Bercu, Taieb Touati

Publication date 6 November 2019

Published in Electronic Communications in Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1810.10590, https://projecteuclid.org/euclid.ecp/1570845629

zbMATH Keywords

martingalesstatistical learningconcentration inequalitiesautoregressive process

Mathematics Subject Classification ID

Gaussian processes (60G15) Inequalities; stochastic orderings (60E15) Martingales with discrete parameter (60G42) Branching processes (Galton-Watson, birth-and-death, etc.) (60J80)

Abstract: We propose new concentration inequalities for self-normalized martingales. The main idea is to introduce a suitable weighted sum of the predictable quadratic variation and the total quadratic variation of the martingale. It offers much more flexibility and allows us to improve previous concentration inequalities. Statistical applications on autoregressive process, internal diffusion-limited aggregation process, and online statistical learning are also provided.

Recommendations

• Exponential inequalities for self-normalized martingales with applications
• Self-normalized exponential inequalities for martingales
• Bernstein type inequalities for self-normalized martingales with applications
• Dzhaparidze-van Zanten type inequalities for self-normalized martingales
• Concentration Inequalities and Martingale Inequalities: A Survey

Cites work

• scientific article; zbMATH DE number 218327 (Why is no real title available?)
• A general class of exponential inequalities for martingales and ratios
• Concentration inequalities for sums and martingales
• Concentration inequalities. A nonasymptotic theory of independence
• Exponential inequalities for martingales with applications
• Exponential inequalities for self-normalized martingales with applications
• Exponential inequalities for self-normalized processes with applications
• Exponential inequalities for sums of weakly dependent variables
• Extensions of the Hoeffding-Azuma inequalities
• Improved Risk Tail Bounds for On-Line Algorithms
• Internal diffusion limited aggregation
• Large deviations for quadratic forms of stationary Gaussian processes
• On tail probabilities for martingales
• On the Bennett-Hoeffding inequality
• On the Generalization Ability of On-Line Learning Algorithms
• Prediction, Learning, and Games
• Probability Inequalities for Sums of Bounded Random Variables
• Pseudo-maximization and self-normalized processes
• The Limiting Distribution of the Serial Correlation Coefficient in the Explosive Case
• Weighted sums of certain dependent random variables

Cited in

(7)

• Exponential inequalities for self-normalized martingales with applications
• Berry-Esseen bounds for self-normalized martingales
• Self-normalized exponential inequalities for martingales
• scientific article; zbMATH DE number 1552475 (Why is no real title available?)
• Dzhaparidze-van Zanten type inequalities for self-normalized martingales
• Exponential inequalities for self-normalized processes with applications
• Bernstein type inequalities for self-normalized martingales with applications

This page was built for publication: New insights on concentration inequalities for self-normalized martingales

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2332992)