On the Prior Sensitivity of Thompson Sampling
From MaRDI portal
Publication:2831392
DOI10.1007/978-3-319-46379-7_22zbMath1480.62025arXiv1506.03378MaRDI QIDQ2831392
Publication date: 9 November 2016
Published in: Lecture Notes in Computer Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1506.03378
62D05: Sampling theory, sample surveys
Related Items
On Bayesian index policies for sequential resource allocation, On the Prior Sensitivity of Thompson Sampling
Cites Work
- Unnamed Item
- Unnamed Item
- Asymptotically efficient adaptive allocation rules
- Sequential experimentation in clinical trials. Design and analysis
- On the Prior Sensitivity of Thompson Sampling
- Approximate Indexability and Bandit Problems with Concave Rewards and Delayed Feedback
- Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis
- Towards Optimal Algorithms for Prediction with Expert Advice
- The Nonstochastic Multiarmed Bandit Problem
- Learning to Optimize via Posterior Sampling
- Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
- Prediction, Learning, and Games