Tight worst-case loss bounds for predicting with expert advice

@inproceedings{Haussler1995TightWL,
  title={Tight worst-case loss bounds for predicting with expert advice},
  author={David Haussler and Jyrki Kivinen and Manfred K. Warmuth},
  booktitle={EuroCOLT},
  year={1995}
}
A b s t r a c t . We consider on-line algorithms for predicting binary outcomes, when the algorithm has available the predictions made by N experts. For a sequence of trials, we compute total losses for both the algorithm and the experts under a loss function. At the end of the trial sequence, we compare the total loss of the algorithm to the total loss of the best expert, i.e., the expert with the least loss on the particular trial sequence. Vovk has introduced a simple algorithm for this… CONTINUE READING

From This Paper

Topics from this paper.
55 Citations
20 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 20 references

Behavior of sequential predictors of binary sequences. In Proceedings of the 4th Prague Conference on Information Theory, Statistical Decision Functions and Random Processes, pages 263{272

  • T. Cover
  • Publishing House of the Czechoslovak Academy of…
  • 1965
Highly Influential
3 Excerpts

Warmuth . The weighted majority algorithm

  • K. M.
  • Information andComputation
  • 1994

Similar Papers

Loading similar papers…