Relaxing the i.i.d. assumption: adaptively minimax optimal regret via root-entropic regularization

DOI10.1214/23-aos2315arXiv2007.06552OpenAlexW3118438270MaRDI QIDQ6183761

Jeffrey Negrea, Daniel M. Roy, Blair L. Bilodeau

Publication date: 4 January 2024

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

Full work available at URL: https://arxiv.org/abs/2007.06552

zbMATH Keywords

aggregationprediction with expert advicesequential decision theoryrobust predictionadaptive minimax regret

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Computational learning theory (68Q32) Minimax procedures in statistical decision theory (62C20) Learning and adaptive systems in artificial intelligence (68T05) Sequential statistical analysis (62L10) Prediction theory (aspects of stochastic processes) (60G25)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Empirical entropy, minimax regret and minimax risk
• Targeted sequential design for targeted learning inference of the optimal treatment rule and its mean reward
• Elementary proof for Sion's minimax theorem
• A Bayesian approach to a problem in sequential estimation
• A game of prediction with expert advice
• The weighted majority algorithm
• A decision-theoretic generalization of on-line learning and an application to boosting
• On minimaxity of follow the leader strategy in the stochastic setting
• An adaptation theory for nonparametric confidence intervals
• Functional aggregation for nonparametric regression.
• Extracting certainty from uncertainty: regret bounded by variation in costs
• Improved second-order bounds for prediction with expert advice
• Fast learning rates in statistical inference through aggregation
• Empirical minimization
• Sequential analysis of comparative clinical trials
• The Nonstochastic Multiarmed Bandit Problem
• Bandit Algorithms
• Stochastic bandits robust to adversarial corruptions
• Learning Theory and Kernel Machines
• Algorithmic Learning Theory
• Prediction, Learning, and Games
• Sequential Compound Estimation
• Consistency of Sequential Binomial Estimates
• Some aspects of the sequential design of experiments
• Sequential Tests of Statistical Hypotheses
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Relaxing the i.i.d. assumption: adaptively minimax optimal regret via root-entropic regularization