Competitive Distribution Estimation: Why is Good-Turing Good Competitive Distribution Estimation: Why is Good-Turing Good
Paper summary The paper gives justification for the widespread use of the Good-Turing estimator for discrete distribution estimation through minimax regret analysis with two comparator classes. The paper obtains competitive regret bounds that lead to a more accurate characterization of the performance of the the Good-Turing estimators and in some cases is much better than the best known risk bounds. The comparator classes considered are estimators with knowledge of the distribution up to permutation, and estimators with full knowledge of the distribution, but with the constraint that the must assign the same probability mass to symbols appearing with the same frequencies.
papers.nips.cc
scholar.google.com
Competitive Distribution Estimation: Why is Good-Turing Good
Orlitsky, Alon and Suresh, Ananda Theertha
Neural Information Processing Systems Conference - 2015 via Bibsonomy
Keywords: dblp


Loading...
Your comment:


Short Science allows researchers to publish paper summaries that are voted on and ranked!
About