2019
DOI: 10.1214/19-ecp269
|View full text |Cite
|
Sign up to set email alerts
|

New insights on concentration inequalities for self-normalized martingales

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.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(7 citation statements)
references
References 28 publications
0
7
0
Order By: Relevance
“…Bercu and Touati [3] obtained that if η k is heavy on left, then (2.14) holds. Thus our condition is analogy of (2.10) in continuous time case.…”
Section: The Main Results and Their Proofsmentioning
confidence: 99%
“…Bercu and Touati [3] obtained that if η k is heavy on left, then (2.14) holds. Thus our condition is analogy of (2.10) in continuous time case.…”
Section: The Main Results and Their Proofsmentioning
confidence: 99%
“…Then, ξ is called heavy on left. Bercu and Touati [14] extended Theorem 1 to general case. Let S = (S n ) n≥0 be a locally square integrable on…”
Section: Propositionmentioning
confidence: 97%
“…Bercu and Touati [14] found that if η k is heavy on the left, then (17) holds. Thus, our condition is an analogy of ( 13) in continuous time case.…”
Section: Propositionmentioning
confidence: 99%
“…In the proofs we will make frequent use of the following iterated exponential martingale inequality which builds on the exponential martingale inequality by Bercu & Touati (2008), see also Bercu et al (2015), Bercu & Touati (2018).…”
Section: A1 Iterated Martingale Inequalitymentioning
confidence: 99%