Stochastic continuum-armed bandits with additive models: minimax regrets and adaptive algorithm

DOI10.1214/22-AOS2182MaRDI QIDQ2091834

Yanyan Li

Publication date: 2 November 2022

Published in: The Annals of Statistics (Search for Journal in Brave)

zbMATH Keywords

self-similarityadaptivityminimax lower boundcurse of dimensionalityoptimal rate of convergenceregretadditive modelcommunication constraintsbandits

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Sequential estimation (62L12)

Related Items (1)

Transfer learning for contextual multi-armed bandits

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Adaptive confidence intervals for regression functions under shape constraints
• Minimax optimal rates of estimation in high dimensional additive models
• Adaptive-treed bandits
• Optimal rates of convergence for covariance matrix estimation
• Fast learning rates for plug-in classifiers
• Asymptotically efficient adaptive allocation rules
• Additive regression and other nonparametric models
• An adaptation theory for nonparametric confidence intervals
• Adaptive confidence interval for pointwise curve estimation.
• Confidence intervals for high-dimensional linear regression: minimax rates and adaptivity
• Confidence bands in density estimation
• Online linear optimization and adaptive routing
• Linearly Parameterized Bandits
• Playing Games with Approximation Algorithms
• Denumerable-Armed Bandits
• Learning Theory
• The Nonstochastic Multiarmed Bandit Problem
• 10.1162/153244303321897663
• A kernel method of estimating structured nonparametric regression based on marginal integration
• The Continuum-Armed Bandit Problem
• Regret and Convergence Bounds for a Class of Continuum-Armed Bandit Problems
• Bandit Algorithms
• MNL-Bandit: A Dynamic Learning Approach to Assortment Selection
• Optimization of Smooth Functions With Noisy Observations: Local Minimax Rates
• Bandits and Experts in Metric Spaces
• Minimax Rates of Estimation for High-Dimensional Linear Regression Over $\ell_q$-Balls
• Stochastic Convex Optimization with Bandit Feedback
• Minimax-optimal rates for sparse additive models over kernel classes via convex programming
• Improved Rates for the Stochastic Continuum-Armed Bandit Problem
• Online Learning with Prior Knowledge
• Some aspects of the sequential design of experiments
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Stochastic continuum-armed bandits with additive models: minimax regrets and adaptive algorithm