Skip to Main content Skip to Navigation
Journal articles

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.
Document type :
Journal articles
Complete list of metadata

Cited literature [20 references]  Display  Hide  Download

https://hal.sorbonne-universite.fr/hal-02345000
Contributor : Gestionnaire Hal-Su <>
Submitted on : Monday, November 4, 2019 - 1:11:49 PM
Last modification on : Thursday, December 10, 2020 - 12:33:18 PM
Long-term archiving on: : Wednesday, February 5, 2020 - 7:05:27 PM

File

euclid.ecp.1570845629.pdf
Publication funded by an institution

Identifiers

Citation

Bernard Bercu, Taieb Touati. New insights on concentration inequalities for self-normalized martingales. Electronic Communications in Probability, Institute of Mathematical Statistics (IMS), 2019, 24, ⟨10.1214/19-ECP269⟩. ⟨hal-02345000⟩

Share

Metrics

Record views

384

Files downloads

914