A CLT and tight lower bounds for estimating entropy

100 citations recorded by the source corpus.

Citations in the corpus

Estimating the unseen: an n/log(n)-sample estimator for entropy and support size, shown optimal via new CLTs (2011, background): “We leverage this central limit theorem to prove a stronger but more speci.c central limit theorem for generalized multinomial distributions a large class of discrete distributions, parameterized by matri * Preliminary full versions, [39] and [40], available at:…”
Minimax Rates of Entropy Estimation on Large Alphabets via Best Polynomial Approximation (2014, background): “For (12) we need to choose a pair of priors, which, in this case, are distributions on the probability simplex M k , is to ensure the entropy values are separated.”
The Power of Linear Estimators (2011, methodology): “Recently, in [27] we showed a central limit theorem, and related tools, that help characterize these distributions in special cases.”
Private Hypothesis Selection (2019, unknown): “If |Σ(i, j)−Σ̂(i, j)| ≤ γ, and I Σ, Proposition 32 of [102] implies:”
Estimating the Unseen (2013, methodology): “In Reference [39], we show that the above performance is optimal in its dependence on k , up to constant factors:”