Empirical Bernstein Inequality for Martingales : Application to Online Learning
Overview & Synopsis
In this article we present a new empirical Bernstein inequality for bounded martingale difference sequences. This inequality refines the one by Freedman [1975] and is then used in order to bound the average risk of the hypotheses during an online learning process. We show theoretical and empirical evidences of the tightness of our result compared with the state of the art bound provided by Cesa-Bianchi and Gentile [2008].
Indexed from repository: HAL Open Science
(
hal.science)
Keyboard Shortcuts:
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | Empirical Bernstein Inequality for Martingales : Application to Online Learning |
|---|---|
| Author / Organization | Thomas Peel, Sandrine Anthoine, Liva Ralaivola |
| Subject & Discipline | Multidisciplinary Academic Open Research |
| Categories | Science & Mathematics |
| Publication Year | 2013 |
| License / Rights | Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
HAL Open Science
(hal.science)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-70330 |
| Original Source Link | Visit Source Page on hal.science » |