Smooth Contextual Bandits: Bridging the Parametric and Nondifferentiable Regret Regimes

DOI10.1287/OPRE.2021.2237MaRDI QIDQ5060501zbMATH OpenOpenAlexFDO

Authors Yichun Hu, Nathan Kallus, Xiaojie Mao

Publication date 10 January 2023

Published in Operations Research (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1909.02553

zbMATH Keywords

contextual banditslocal polynomial regressionmargin conditionminimax regret

Mathematics Subject Classification ID

Statistics (62-XX)

Cites work

• A linear response bandit problem
• An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels
• Asymptotically efficient adaptive allocation rules
• Bandit problems with side observations
• Consistent nonparametric regression. Discussion
• Fast learning rates for plug-in classifiers
• Finite-time analysis of the multiarmed bandit problem
• scientific article; zbMATH DE number 1306865 (Why is no real title available?)
• scientific article; zbMATH DE number 3222478 (Why is no real title available?)
• Local Rademacher complexities
• Online decision making with high-dimensional covariates
• Optimal aggregation of classifiers in statistical learning.
• Optimal global rates of convergence for nonparametric regression
• Optimal rates of convergence for nonparametric estimators
• Prediction, Learning, and Games
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• Smooth discrimination analysis
• Some new asymptotic theory for least squares series: pointwise and uniform results
• The k-nearest neighbour UCB algorithm for multi-armed bandits with covariates
• The multi-armed bandit problem with covariates
• Woodroofe's one-armed bandit problem revisited

Cited in

(3)

• Greedy Algorithm Almost Dominates in Smoothed Contextual Bandits
• Transfer learning for contextual multi-armed bandits
• Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes

This page was built for publication: Smooth Contextual Bandits: Bridging the Parametric and Nondifferentiable Regret Regimes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5060501)