2019
DOI: 10.1109/tcyb.2017.2779140
|View full text |Cite
|
Sign up to set email alerts
|

Multiplicative Update Methods for Incremental Quantile Estimation

Abstract: We present a novel lightweight incremental quantile estimator which possesses far less complexity than the Tierney's estimator and its extensions. Notably, our algorithm relies only on tuning one single parameter which is a plausible property which we could only find in the discretized quantile estimator Frugal. This makes our algorithm easy to tune for better performance. Furthermore, our algorithm is multiplicative which makes it highly suitable to handle quantile estimation in systems in which the underlyin… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
63
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
3
2

Relationship

4
1

Authors

Journals

citations
Cited by 23 publications
(63 citation statements)
references
References 33 publications
0
63
0
Order By: Relevance
“…It is possible to prove that the DUMIQE approach in (1) converges to the true quantiles [5]. Unfortunately, it is hard (or impossible) to prove convergence for the methods described above.…”
Section: Methodsmentioning
confidence: 99%
See 3 more Smart Citations
“…It is possible to prove that the DUMIQE approach in (1) converges to the true quantiles [5]. Unfortunately, it is hard (or impossible) to prove convergence for the methods described above.…”
Section: Methodsmentioning
confidence: 99%
“…To achieve this, we extend the DUMIQE method proposed by Yazidi and Hammer [5]. The choice of DUMIQE method as a core for our current work is deliberate since it was shown to be the most performant method in the literature.…”
Section: Introductionmentioning
confidence: 99%
See 2 more Smart Citations
“…For more recent methods we can mention the Frugal methods [12] which runs a discrete Markov chain and estimates quantiles of discrete probability distribution. Yazidi and Hammer (2016) [18] proposed a version of the Frugal method that works on continuous sample spaces in addition to an improved version, based on deterministic updates. A disadvantage with the incremental methods referred to above is that they are constructed to estimate only a single quantile of the data stream.…”
Section: Introductionmentioning
confidence: 99%