How to use expert advice

@inproceedings{CesaBianchi1993HowTU,
  title={How to use expert advice},
  author={N. Cesa-Bianchi and Y. Freund and D. Helmbold and D. Haussler and R. Schapire and Manfred K. Warmuth},
  booktitle={STOC '93},
  year={1993}
}
  • N. Cesa-Bianchi, Y. Freund, +3 authors Manfred K. Warmuth
  • Published in STOC '93 1993
  • Mathematics, Computer Science
  • We analyze algorithms that predict a binary value by combining the predictions of several prediction strategies, called `experts''. Our analysis is for worst-case situations, i.e., we make no assumptions about the way the sequence of bits to be predicted is generated. We measure the performance of the algorithm by the difference between the expected number of mistakes it makes on the bit sequence and the expected number of mistakes made by the best expert on this sequence, where the expectation… CONTINUE READING
    611 Citations

    Figures and Topics from this paper

    Tight worst-case loss bounds for predicting with expert advice
    • 102
    • PDF
    On-line evaluation and prediction using linear functions
    • 12
    How to Better Use Expert Advice
    • 23
    • PDF
    Theory and applications of predictors that specialize
    • Highly Influenced
    • PDF
    Using and combining predictors that specialize
    • 247
    • PDF
    Averaging Expert Predictions
    • 137
    • PDF
    Towards Optimal Algorithms for Prediction with Expert Advice
    • 38
    • Highly Influenced
    • PDF
    Online Learning with Many Experts
    • 3
    • PDF