Statistical complexity and optimal algorithms for nonlinear ridge bandits

DOI10.1214/24-AOS2395MaRDI QIDQ7035874zbMATH OpenFDO

Authors Nived Rajaraman, Yanjun Han, Jiantao Jiao, Kannan Ramchandran

Publication date 29 January 2025

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

Full work available at URL https://projecteuclid.org/journals/annals-of-statistics/volume-52/issue-6/Statistical-complexity-and-optimal-algorithms-for-nonlinear-ridge-bandits/10.1214/24-AOS2395.full

zbMATH Keywords

adaptive samplingbandit problemsminimax rateregret boundsridge functionssequential estimation

Mathematics Subject Classification ID

Minimax procedures in statistical decision theory (62C20) Optimal statistical designs (62K05) Sequential estimation (62L12)

Cites work

• 10.1162/153244303321897663
• A class of measures of informativity of observation channels
• Asymptotic theory of sequential estimation: Differential geometrical approach
• Asymptotically efficient adaptive allocation rules
• Bandit algorithms
• Bandit problems with infinitely many arms
• Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits Under Realizability
• Explore first, exploit next: the true shape of regret in bandit problems
• Exponential lower bounds for planning in MDPs with linearly-realizable optimal action-value functions
• scientific article; zbMATH DE number 3638998 (Why is no real title available?)
• Improved regret for zeroth-order adversarial bandit convex optimisation
• Information-Based Complexity, Feedback and Dynamics in Convex Programming
• Kernel-based methods for bandit convex optimization
• Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges
• Nonparametric and semiparametric models.
• On the Number of Iterations of Piyavskii's Global Optimization Algorithm
• Online convex optimization in the bandit setting: gradient descent without a gradient
• Optimal reconstruction of a function from its projections
• Optimum Character of the Sequential Probability Ratio Test
• Reinforcement learning. An introduction
• Riemannian metrics on convex sets with applications to Poincaré and log-Sobolev inequalities
• Sequential Design of Experiments
• SEQUENTIAL DISCRIMINATION OF HYPOTHESES WITH CONTROL OF OBSERVATIONS
• Sequential estimation of the largest normal mean when the variance is known
• Sequential Experimental Design Procedures
• Some aspects of the sequential design of experiments
• Statistical complexity and optimal algorithms for nonlinear ridge bandits
• The Capacity of Channels With Feedback
• The Nonstochastic Multiarmed Bandit Problem

Cited in

(2)

• Statistical complexity and optimal algorithms for nonlinear ridge bandits
• Estimation of discrete distributions in relative entropy, and the deviations of the missing mass

This page was built for publication: Statistical complexity and optimal algorithms for nonlinear ridge bandits

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7035874)