Combinatorial Bandits

  title={Combinatorial Bandits},
  author={Nicol{\`o} Cesa-Bianchi and G{\'a}bor Lugosi},
  journal={J. Comput. Syst. Sci.},
We study sequential prediction problems in which, at each time instance, the forecaster chooses a vector from a given finite set S ⊆ R. At the same time, the opponent chooses a “loss” vector in R and the forecaster suffers a loss that is the inner product of the two vectors. The goal of the forecaster is to achieve that, in the long run, the accumulated loss is not much larger than that of the best possible element in S. We consider the “bandit” setting in which the forecaster only has access… CONTINUE READING
Highly Influential
This paper has highly influenced 21 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 161 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.
105 Citations
29 References
Similar Papers


Publications citing this paper.

161 Citations

Citations per Year
Semantic Scholar estimates that this publication has 161 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 29 references

Hedging structured concepts

  • W. M. Koolen, M. K. Warmuth, J. Kivinen
  • in: Proceedings of 23rd Annual Conference on…
  • 2010
1 Excerpt

Similar Papers

Loading similar papers…