• Computer Science
  • Published in NIPS 2016

Adaptive Concentration Inequalities for Sequential Decision Problems

@inproceedings{Zhao2016AdaptiveCI,
  title={Adaptive Concentration Inequalities for Sequential Decision Problems},
  author={Shengjia Zhao and Enze Zhou and Ashish Sabharwal and Stefano Ermon},
  booktitle={NIPS},
  year={2016}
}
A key challenge in sequential decision problems is to determine how many samples are needed for an agent to make reliable decisions with good probabilistic guarantees. We introduce Hoeffding-like concentration inequalities that hold for a random, adaptively chosen number of samples. Our inequalities are tight under natural assumptions and can greatly simplify the analysis of common sequential decision problems. In particular, we apply them to sequential hypothesis testing, best arm… CONTINUE READING

Figures and Topics from this paper.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
SHOWING 1-10 OF 14 CITATIONS

Bounding Regret in Empirical Games

VIEW 1 EXCERPT
CITES BACKGROUND

Foundations of Large-Scale Sequential Experimentation

VIEW 1 EXCERPT
CITES BACKGROUND

Incentivizing Exploration by Heterogeneous Users

VIEW 2 EXCERPTS
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 22 REFERENCES

Best-arm identification algorithms for multi-armed bandits in the fixed confidence setting

VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

Noisy binary search and its applications

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

On the optimal sample complexity for best arm identification

  • Lijie Chen, Jian Li
  • CoRR, abs/1511.03774,
  • 2015
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Almost Optimal Exploration in Multi-Armed Bandits

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Prediction, learning, and games

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Karp and Robert Kleinberg . Noisy binary search and its applications

  • M Richard
  • 2013