Learning to Optimize Under Non-Stationarity
Name
1810.03024.pdf
Description
Accepted version
Size
417.38 KB
Format
Adobe PDF
Checksum (MD5)
e8499fabc0c4f819685a18106fbb58ca
Author(s)
Cheung, Wang Chi
Simchi-Levi, David
Zhu, Ruihao
Date Issued
2018
Journal
AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics
Publisher
Elsevier BV
Citation
Cheung, Wang Chi, Simchi-Levi, David and Zhu, Ruihao. 2018. "Learning to Optimize Under Non-Stationarity." AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics, 89.
Version
Author's final manuscript
Abstract
© 2019 by the author(s). We introduce algorithms that achieve state-of-the-art dynamic regret bounds for non-stationary linear stochastic bandit setting. It captures natural applications such as dynamic pricing and ads allocation in a changing environment. We show how the difficulty posed by the non-stationarity can be overcome by a novel marriage between stochastic and adversarial bandits learning algorithms. Defining d, BT, and T as the problem dimension, the variation budget, and the total time horizon, respectively, our main contributions are the tuned Sliding Window UCB (SW-UCB) algorithm with optimal Oe(d2/3(BT + 1)1/3T2/3) dynamic regret, and the tuning free bandit-over-bandit (BOB) framework built on top of the SW-UCB algorithm with best Oe(d2/3(BT + 1)1/4T3/4) dynamic regret.
MIT Department
Massachusetts Institute of Technology. Institute for Data, Systems, and Society
Statistics and Data Science Center (Massachusetts Institute of Technology)
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.2139/ssrn.3261050
