|
Activity Number:
|
270
- Advanced Multivariate Time Series Modeling
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, August 9, 2022 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
International Chinese Statistical Association
|
|
Abstract #322642
|
|
|
Title:
|
Recursive Quantile Estimation: Non-Asymptotic Confidence Bounds
|
|
Author(s):
|
Likai Chen* and Wei Biao Wu and Georg Keilbar
|
|
Companies:
|
Washington University in Saint Louis and University of Chicago and University of Vienna
|
|
Keywords:
|
stochastic gradient descent;
quantiles;
finite sample bounds
|
|
Abstract:
|
This papers considers the recursive estimation of quantiles using the stochastic gradient descent (SGD) algorithm with Polyak-Ruppert averaging. The algorithm offers a compu- tationally and memory efficient alternative to the usual empirical estimator. Our focus is on studying the non-asymptotic behavior by providing exponentially decreasing tail proba- bility bounds under minimal assumptions on the smoothness of the density function. This novel non-asymptotic result is based on a bound of the moment generating function of the SGD estimate. We apply our result to the problem of best arm identification in a multi-armed stochastic bandit setting under quantile preference.
|
Authors who are presenting talks have a * after their name.
