Consistency of weighted majority votes

@inproceedings{Berend2014ConsistencyOW,
  title={Consistency of weighted majority votes},
  author={Daniel Berend and Aryeh Kontorovich},
  booktitle={NIPS},
  year={2014}
}
We revisit from a statistical learning perspective the classical decision-theoretic problem of weighted expert voting. In particular, we examine the consistency (both asymptotic and finitary) of the optimal Nitzan-Paroush weighted majority and related rules. In the case of known expert competence levels, we give sharp error estimates for the optimal rule. When the competence levels are unknown, they must be empirically estimated. We provide frequentist and Bayesian analyses for this situation… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 5 times over the past 90 days. VIEW TWEETS

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 34 references

Minimax Optimal Convergence Rates for Estimating Ground Truth from Crowdsourced Labels

  • C. Gao, D. Zhou
  • 2014
1 Excerpt

When is Condorcet ’ s jury theorem valid ?

  • J. Paroush D. Berend
  • Soc . Choice Welfare
  • 2014

A sharp estimate of the binomial mean absolute deviation with applications

  • D. Berend, A. Kontorovich
  • Statistics & Probability Letters, 83(4):1254–1259…
  • 2013

Concentration of measure inequalities in information theory, communications and coding

  • M. Raginsky, I. Sason
  • Foundations and Trends in Communications and…
  • 2013
1 Excerpt

Similar Papers

Loading similar papers…