|
| | | | |
| | | |
| Stat |
Members: 3645
Articles: 2'501'711
Articles rated: 2609
19 April 2024 |
|
| | | | |
|
Article overview
| |
|
|
A Concentration Bound for Stochastic Approximation via Alekseev's Formula | | Gugan Thoppe
; Vivek S. Borkar
; | | Date: |
26 Jun 2015 | | Abstract: | In this paper, we obtain a lower bound on the probability that the stochastic
approximation iterates remain in the $epsilon-$neighborhood of a desired
solution from some time $n_0 + au$ onwards given that the $n_0-$th iterate
was in some bigger neighbourhood of this solution. For this, we use the
Alekseev’s analog of the variation of constants formula for nonlinear systems
and a concentration inequality for martingales, which we prove separately. Our
bound holds under significantly weaker hypotheses as compared to available
results in similar vein. | | Source: | arXiv, 1506.8657 | | Services: | Forum | Review | PDF | Favorites | |
|
|
No review found.
Did you like this article?
Note: answers to reviews or questions about the article must be posted in the forum section.
Authors are not allowed to review their own article. They can use the forum section.
browser Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)
|
| |
|
|
|
|
News, job offers and information for researchers and scientists:
| |
REGISTER