Smooth contextual bandits : bridging the parametric and nondifferentiable regret regimes
Year of publication: |
2022
|
---|---|
Authors: | Hu, Yichun ; Kallus, Nathan ; Mao, Xiaojie |
Published in: |
Operations research. - Linthicum, Md. : INFORMS, ISSN 1526-5463, ZDB-ID 2019440-7. - Vol. 70.2022, 6, p. 3261-3281
|
Subject: | contextual bandits | local polynomial regression | Machine Learning and Data Science | margin condition | minimax regret | Künstliche Intelligenz | Artificial intelligence | Regressionsanalyse | Regression analysis | Entscheidung unter Unsicherheit | Decision under uncertainty | Schätztheorie | Estimation theory |
-
Athey, Susan, (2017)
-
Subset selection with shrinkage : sparse linear modeling when the SNR is low
Mazumder, Rahul, (2023)
-
Algorithm is experiment : machine learning, market design, and policy eligibility rules
Narita, Yusuke, (2021)
- More ...
-
Fast rates for contextual linear optimization
Hu, Yichun, (2022)
-
Fast rates for the regret of offline reinforcement learning
Hu, Yichun, (2025)
-
Fairness Under Unawareness : Assessing Disparity When Protected Class Is Unobserved
Chen, Jiahao, (2018)
- More ...