Simple Bayesian Algorithms for Best-Arm Identification
From MaRDI portal
Publication:5144786
DOI10.1287/opre.2019.1911zbMath1458.91111arXiv1602.08448OpenAlexW3016967565MaRDI QIDQ5144786
Publication date: 19 January 2021
Published in: Operations Research (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1602.08448
Resource and cost allocation (including fair division, apportionment, etc.) (91B32) Mathematical economics and fuzziness (91B86)
Related Items (7)
Robust Learning of Consumer Preferences ⋮ Posterior-Based Stopping Rules for Bayesian Ranking-and-Selection Procedures ⋮ An index-based deterministic convergent optimal algorithm for constrained multi-armed bandit problems ⋮ On the finite-sample statistical validity of adaptive fully sequential procedures ⋮ Learning the distribution with largest mean: two bandit frameworks ⋮ Complete expected improvement converges to an optimal budget allocation ⋮ Dismemberment and design for controlling the replication variance of regret for the multi-armed bandit
Cites Work
- Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges
- Handbook of simulation optimization
- Second order efficiency in the sequential design of experiments
- Asymptotically efficient adaptive allocation rules
- On the consistency of Bayes estimates
- The center of a system of non-parallel forces
- Simulation budget allocation for further enhancing the efficiency of ordinal optimization
- On Bayesian index policies for sequential resource allocation
- Bayesian statistics and the efficiency and ethics of clinical trials
- Convergence rates of posterior distributions.
- Bayesian look ahead one-stage sampling allocations for selection of the best population
- The consistency of posterior distributions in nonparametric problems
- Active sequential hypothesis testing
- The Knowledge Gradient Algorithm for a General Class of Online Learning Problems
- Sequential Sampling to Myopically Maximize the Expected Value of Information
- A Fully Sequential Elimination Procedure for Indifference-Zone Ranking and Selection with Tight Bounds on Probability of Correct Selection
- Indifference-Zone-Free Selection of the Best
- On the Convergence Rates of Expected Improvement Methods
- Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis
- Sequential Design of Experiments
- A Knowledge-Gradient Policy for Sequential Information Collection
- Pure Exploration in Multi-armed Bandits Problems
- The Sequential Design of Experiments for Infinitely Many States of Nature
- On two-stage selection procedures and related probability-inequalities
- Efficient Ranking and Selection in Parallel Computing Environments
- Learning to Optimize via Information-Directed Sampling
- Online Network Revenue Management Using Thompson Sampling
- Stochastically Constrained Ranking and Selection via SCORE
- Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
- Controlled Sensing for Multihypothesis Testing
- A Sequential Procedure for Selecting the Population with the Largest Mean from $k$ Normal Populations
- On the Asymptotic Behavior of Bayes' Estimates in the Discrete Case
- Asymptotically Optimum Sequential Inference and Design
- A Single-Sample Multiple Decision Procedure for Ranking Means of Normal Populations with known Variances
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
This page was built for publication: Simple Bayesian Algorithms for Best-Arm Identification
