On the Bias, Risk, and Consistency of Sample Means in Multi-armed Bandits
From MaRDI portal
Publication:5018902
DOI10.1137/20M1361249zbMath1476.62032arXiv1902.00746OpenAlexW3216378235MaRDI QIDQ5018902
Aaditya Ramdas, Alessandro Rinaldo, Jaehyeok Shin
Publication date: 27 December 2021
Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1902.00746
Asymptotic properties of nonparametric inference (62G20) Sampling theory, sample surveys (62D05) Statistical aspects of big data and data science (62R07)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges
- \(L_p\)-version of the Dubins-Savage inequality and some exponential inequalities
- On confidence sequences
- Estimation of densities and applications
- Information-theoretic determination of minimax rates of convergence
- Self-normalized processes: exponential inequalities, moment bounds and iterated logarithm laws.
- Time-uniform, nonparametric, nonasymptotic confidence sequences
- Time-uniform Chernoff bounds via nonnegative supermartingales
- Stopped Random Walks
- Estimation Following Sequential Tests
- Probability
- Bandit Algorithms
- On the Asymptotic Efficiency of a Sequential Procedure for Estimating the Mean
- CONFIDENCE SEQUENCES FOR MEAN, VARIANCE, AND MEDIAN
- SOME FURTHER REMARKS ON INEQUALITIES FOR SAMPLE SUMS
- Further Remarks on Sequential Estimation: The Exponential Case
- Optimum Character of the Sequential Probability Ratio Test
- Some aspects of the sequential design of experiments
- Introduction to nonparametric estimation
- Relative loss bounds for on-line density estimation with the exponential family of distributions
This page was built for publication: On the Bias, Risk, and Consistency of Sample Means in Multi-armed Bandits