Corpus ID: 13981088

Generalized Thompson Sampling for Contextual Bandits

@article{Li2013GeneralizedTS,
  title={Generalized Thompson Sampling for Contextual Bandits},
  author={L. Li},
  journal={ArXiv},
  year={2013},
  volume={abs/1310.7163}
}
  • L. Li
  • Published 2013
  • Mathematics, Computer Science
  • ArXiv
Thompson Sampling, one of the oldest heuristics for solving multi-armed bandits, has recently been shown to demonstrate state-of-the-art performance. The empirical success has led to great interests in theoretical understanding of this heuristic. In this paper, we approach this problem in a way very different from existing efforts. In particular, motivated by the connection between Thompson Sampling and exponentiated updates, we propose a new family of algorithms called Generalized Thompson… Expand
17 Citations
On the Prior Sensitivity of Thompson Sampling
  • 14
  • PDF
(Sequential) Importance Sampling Bandits
  • 3
  • PDF
Learning to Optimize via Posterior Sampling
  • 350
  • PDF
Near-Optimal Regret Bounds for Thompson Sampling
  • 43
  • PDF
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
  • 299
  • PDF
Thompson Sampling for Bandit Problems
  • PDF
A Near-optimal Regret Bounds for
  • 1
  • PDF
Real-Time Bid Prediction using Thompson Sampling-Based Expert Selection
  • 4
Online Stochastic Linear Optimization under One-bit Feedback
  • 32
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 32 REFERENCES
Thompson Sampling for Contextual Bandits with Linear Payoffs
  • 507
  • PDF
Learning to Optimize via Posterior Sampling
  • 350
  • Highly Influential
  • PDF
Further Optimal Regret Bounds for Thompson Sampling
  • 291
  • PDF
Analysis of Thompson Sampling for the Multi-armed Bandit Problem
  • 719
  • PDF
Optimistic Bayesian Sampling in Contextual-Bandit Problems
  • 175
  • PDF
Parametric Bandits: The Generalized Linear Case
  • 246
  • PDF
The Epoch-Greedy algorithm for contextual multi-armed bandits
  • 297
  • PDF
Contextual Bandits with Linear Payoff Functions
  • 526
  • PDF
A modern Bayesian look at the multi-armed bandit
  • 348
  • PDF
An Empirical Evaluation of Thompson Sampling
  • 904
  • PDF
...
1
2
3
4
...